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

    Neuronpedia

    INDEX
    Explanations

    instances of quotation marks and backticks, indicating text formatting or code references

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

    "AS IS" BASIS

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵↵
    -0.59
    ↵
    -0.49
    /
    -0.44
    a
    -0.42
    D
    -0.40
    b
    -0.40
    0
    -0.39
    A
    -0.39
    E
    -0.39
    用
    -0.39
    POSITIVE LOGITS
     autorytatywna
    0.91
    Rhestr
    0.91
    ]")]
    0.85
    zzleHttp
    0.82
    IsContent
    0.82
     snippetHide
    0.81
    InputBorder
    0.79
    ftagPool
    0.78
    "]);
    0.78
    GOTREF
    0.75
    Act Density 0.038%

    No Known Activations