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

    Neuronpedia

    INDEX
    Explanations

    things related to user input, forms, and credentials

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    MEASURE
    -0.54
     Test
    -0.50
    overhead
    -0.47
     gab
    -0.46
     delan
    -0.46
    Overhead
    -0.45
    Measurements
    -0.44
     Training
    -0.44
    Measurement
    -0.44
     test
    -0.43
    POSITIVE LOGITS
    ValueStyle
    1.05
    0.86
     للمعارف
    0.84
    \{\\
    0.84
     ModelExpression
    0.79
     للاسماء
    0.74
    EndInit
    0.73
    RenderAtEndOf
    0.72
     typelib
    0.69
    ">:
    0.69
    Act Density 0.178%

    No Known Activations