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

    Neuronpedia

    INDEX
    Explanations

    dress code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    t
    2.03
    נה
    1.95
    j
    1.95
    ă
    1.83
     disadvant
    1.77
     Specification
    1.76
    m
    1.67
    PA
    1.66
     décrites
    1.63
    1.62
    POSITIVE LOGITS
    如同
    2.22
    های
    2.03
    donor
    2.03
     亠
    2.03
    こんばんは
    2.03
     libid
    2.02
    ी
    2.02
    (',
    1.97
     する
    1.95
    ﻟ
    1.95
    Act Density 0.006%

    No Known Activations