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

    Neuronpedia

    INDEX
    Explanations

    strings enclosed in quotes or special characters

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

    code snippets and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ),
    -0.59
    **,
    -0.58
    》,
    -0.54
    ,
    -0.53
    (),
    -0.52
    )،
    -0.51
    ~,
    -0.51
    ],
    -0.51
    (),
    -0.50
     noqa
    -0.50
    POSITIVE LOGITS
    abcdefghijklmnop
    0.70
    setVerticalGroup
    0.52
     "";
    0.45
     createSlice
    0.43
    phorus
    0.43
     wł
    0.43
    =$?
    0.41
    ';
    0.41
    رون
    0.41
    rigado
    0.40
    Act Density 0.017%

    No Known Activations