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

    Neuronpedia

    INDEX
    Explanations

    J-prefixed technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     madrugada
    0.69
    prime
    0.66
     নবাব
    0.64
     பட
    0.63
     j
    0.63
     корпу
    0.63
    달
    0.63
    SIMPLEX
    0.62
     আবদুল্লাহ
    0.62
     корпуса
    0.62
    POSITIVE LOGITS
     Boss
    0.82
     coalitions
    0.80
    SPs
    0.79
    BOSS
    0.78
    Bos
    0.78
    boss
    0.77
    Boss
    0.77
     Coal
    0.77
     Bos
    0.75
     بجلی
    0.74
    Act Density 0.002%

    No Known Activations