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

    Neuronpedia

    INDEX
    Explanations

    fighting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    *pow
    -0.08
    ﻮ
    -0.07
    .ToLower
    -0.07
    uffling
    -0.07
    nable
    -0.07
    缩
    -0.07
     جو
    -0.07
     свою
    -0.07
    しました
    -0.07
     quantify
    -0.07
    POSITIVE LOGITS
     δημιουργ
    0.06
     Pics
    0.06
    toggleClass
    0.06
    adil
    0.06
     daycare
    0.06
     thiện
    0.06
    ussions
    0.06
     MatDialog
    0.05
    itom
    0.05
    tik
    0.05
    Act Density 0.002%

    No Known Activations