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

    Neuronpedia

    INDEX
    Explanations

    action or capability

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Hình
    0.90
    Từ
    0.85
    Chiều
    0.84
     ร้าน
    0.82
     racconta
    0.80
    سين
    0.80
     Quelles
    0.80
    يفة
    0.79
    RELAND
    0.79
    ivité
    0.79
    POSITIVE LOGITS
    ction
    0.82
    o
    0.82
    ging
    0.79
    z
    0.73
    displays
    0.71
    do
    0.71
    тся
    0.70
     w
    0.68
    ll
    0.68
    ur
    0.68
    Act Density 0.001%

    No Known Activations