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

    Neuronpedia

    INDEX
    Explanations

    definitions and qualifications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    黟
    0.48
     Moderators
    0.46
    駒
    0.45
    Analytics
    0.44
    ﻓ
    0.44
    デザイナー
    0.44
    ველ
    0.43
     anticancer
    0.43
     പ്രസിഡ
    0.43
    勰
    0.43
    POSITIVE LOGITS
    t
    0.56
    ist
    0.55
    es
    0.47
    ophone
    0.46
    ton
    0.46
    sn
    0.46
     beteg
    0.46
    ecia
    0.45
    iemi
    0.45
    eny
    0.45
    Act Density 0.002%

    No Known Activations