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

    Neuronpedia

    INDEX
    Explanations

    numbers and lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Telangana
    1.01
     yattha
    0.97
     pessoais
    0.95
    ৤
    0.95
    Ⴖ
    0.95
     Конгрегация
    0.95
     Diput
    0.94
    ஜ்மஹ
    0.94
     Şubat
    0.93
     imassa
    0.92
    POSITIVE LOGITS
    ↵
    0.87
    aming
    0.79
    D
    0.73
    َ
    0.70
    ات
    0.69
    DU
    0.69
    ating
    0.66
    (
    0.64
    ruck
    0.63
    Better
    0.63
    Act Density 0.042%

    No Known Activations