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

    Neuronpedia

    INDEX
    Explanations

    suffixes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <bos>
    -0.42
    '
    -0.40
    chale
    -0.39
    ↵↵
    -0.37
    ↵
    -0.37
     "
    -0.35
    bacher
    -0.35
    ’
    -0.35
     regioni
    -0.34
    up
    -0.34
    POSITIVE LOGITS
     kasarigan
    1.12
    IsMutable
    0.93
    parsedMessage
    0.89
     سكانية
    0.89
    StructEnd
    0.87
     الحره
    0.86
     referenties
    0.85
    FieldBuilder
    0.83
    __*/
    0.80
     فريبيس
    0.78
    Act Density 0.030%

    No Known Activations