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

    Neuronpedia

    INDEX
    Explanations

    scientific research papers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    еру
    -0.06
    ference
    -0.06
    RP
    -0.06
    iesz
    -0.06
    rok
    -0.06
    animations
    -0.06
    랜드
    -0.06
    roc
    -0.06
     userDao
    -0.06
    ’te
    -0.06
    POSITIVE LOGITS
     Himal
    0.07
     Bras
    0.07
     내용
    0.06
    _supp
    0.06
     liber
    0.06
     STAT
    0.06
    ステ
    0.06
     τρό
    0.06
     Çalış
    0.06
    tyard
    0.06
    Act Density 0.016%

    No Known Activations