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

    Neuronpedia

    INDEX
    Explanations

    building success from failure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    e
    0.67
    on
    0.63
    es
    0.59
    s
    0.57
    *
    0.52
    ll
    0.51
    al
    0.51
    {
    0.50
    t
    0.49
    <
    0.48
    POSITIVE LOGITS
     encontrar
    0.57
     व्यास
    0.54
    પુર
    0.54
     반지름
    0.52
     sedent
    0.52
     사용하여
    0.52
     વિશ્વ
    0.52
     conseguir
    0.51
     المصفوفه
    0.51
     фаразы
    0.51
    Act Density 0.002%

    No Known Activations