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

    Neuronpedia

    INDEX
    Explanations

    javascript type/state checks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     キャンペーン
    -2.27
     ランチ
    -2.11
     Verbs
    -2.03
    臯
    -1.96
    〜〜
    -1.88
    檮
    -1.88
    𔘓
    -1.83
     朋友
    -1.83
     Beteiligung
    -1.82
     本店
    -1.81
    POSITIVE LOGITS
    able
    2.34
    ’
    2.06
    潆
    1.95
     a
    1.89
    de
    1.88
    ization
    1.87
    。“
    1.87
     precaution
    1.87
     \
    1.85
    ers
    1.81
    Act Density 0.003%

    No Known Activations