Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    structures related to programming and data handling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    code identifiers and programming terms

    np_acts-logits-general · gemini-2.5-flash-lite

    tokens that look like code or technical identifiers (numeric, underscore- or camelCase-containing names, ports/ids/keys and other config/JSON/code-like tokens).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
    VersionUID
    -0.67
     invokingState
    -0.64
    Personendaten
    -0.63
    MemoryWarning
    -0.61
     ब्रेकडाउन
    -0.60
    TagMode
    -0.60
    WriteTagHelper
    -0.57
    GraphicsUnit
    -0.57
    addContainerGap
    -0.56
    原始内容存档于
    -0.55
    POSITIVE LOGITS
    }}">
    0.47
    ]]]
    0.41
    ″]
    0.41
     even
    0.40
    Dieser
    0.39
    >');
    0.39
    }))
    0.38
    Even
    0.36
    生
    0.35
    This
    0.35
    Act Density 19.105%

    No Known Activations