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

    Neuronpedia

    INDEX
    Explanations

    number theory concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    UN
    0.82
    0.80
    [
    0.76
    :
    0.75
    id
    0.75
     :
    0.70
     Earth
    0.70
     UN
    0.70
     I
    0.69
     A
    0.68
    POSITIVE LOGITS
     variabili
    0.98
    origData
    0.96
     кеңсеси
    0.96
    BESCHREIBUNG
    0.92
    🚤
    0.92
     кеңсесинде
    0.91
     soluciones
    0.90
    stven
    0.89
     modificación
    0.89
    〽
    0.88
    Act Density 0.001%

    No Known Activations