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

    Neuronpedia

    INDEX
    Explanations

    function definitions and method calls in code

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

    python `self`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Italijanski
    -0.82
    лтамалар
    -0.79
     Italijani
    -0.77
    Ӕ
    -0.71
     kaarangay
    -0.70
    jsii
    -0.67
    Personendaten
    -0.66
     Италијани
    -0.63
    GTCX
    -0.63
     ویکی‌پدی
    -0.62
    POSITIVE LOGITS
     doInBackground
    0.39
     is
    0.39
    __(
    0.35
     you
    0.35
     spirituelle
    0.34
     umat
    0.34
     habet
    0.33
    or
    0.31
    ViewFeatures
    0.31
    is
    0.30
    Act Density 0.001%

    No Known Activations