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

    Neuronpedia

    INDEX
    Explanations

    stadium

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    し
    0.97
    ž
    0.87
    কে
    0.86
    ：
    0.82
     a
    0.81
    Да
    0.80
    РИ
    0.79
    তে
    0.79
    US
    0.78
    కు
    0.77
    POSITIVE LOGITS
    ت
    1.06
     asociaciones
    0.97
     enzimas
    0.96
     alteraciones
    0.93
    .
    0.91
     formas
    0.91
     entidades
    0.91
     goles
    0.89
    {
    0.89
     equipos
    0.89
    Act Density 0.001%

    No Known Activations