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

    Neuronpedia

    INDEX
    Explanations

    manuscript preparation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     судо
    0.77
    time
    0.72
     समय
    0.69
    to
    0.68
    번호
    0.64
    man
    0.63
     Hadley
    0.63
     प्रयोग
    0.63
     trị
    0.62
     bilangan
    0.61
    POSITIVE LOGITS
    el
    1.02
     inici
    0.99
    il
    0.92
     powied
    0.91
    න
    0.89
    Puedes
    0.84
    '}
    0.82
    T
    0.81
    ين
    0.79
    }
    0.77
    Act Density 0.002%

    No Known Activations