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

    Neuronpedia

    INDEX
    Explanations

    javascript code, specifically syntax like brackets, colons, and file paths

    oai_token-act-pair · gemini-2.0-flash

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ValueStyle
    -1.10
     ExecuteAsync
    -1.09
    دانشنامهٔ
    -0.91
     resourceCulture
    -0.90
    IndentedString
    -0.86
     transfieras
    -0.84
    InjectAttribute
    -0.84
     تضيفلها
    -0.82
    IntoConstraints
    -0.82
     ProtoMessage
    -0.81
    POSITIVE LOGITS
    !
    0.50
     v
    0.48
     c
    0.46
     
    0.46
     T
    0.45
    raw
    0.43
    ITOS
    0.43
     le
    0.41
     Commission
    0.41
     t
    0.40
    Act Density 0.905%

    No Known Activations