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

    Neuronpedia

    INDEX
    Explanations

    damage from

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ab
    0.51
    eas
    0.48
    bees
    0.46
    color
    0.46
    as
    0.45
     ales
    0.45
    А
    0.45
    date
    0.44
    igans
    0.44
     este
    0.44
    POSITIVE LOGITS
    :"))
    0.48
    审批
    0.45
    ত্রে
    0.44
    ()")
    0.44
     Gulf
    0.44
    偐
    0.43
     RasterModelGrid
    0.43
    漱
    0.43
     Evangel
    0.43
     Inet
    0.42
    Act Density 0.003%

    No Known Activations