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

    Neuronpedia

    INDEX
    Explanations

    table differences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    layered
    0.88
    digit
    0.80
    ؛
    0.80
    Biblioteca
    0.78
    ând
    0.76
    кове
    0.73
    readme
    0.73
    र्थ
    0.73
    став
    0.73
    informations
    0.72
    POSITIVE LOGITS
     是否
    0.84
     kawaida
    0.79
     Usually
    0.78
     defecto
    0.73
     Type
    0.72
     tertinggi
    0.72
     cenderung
    0.72
     Govt
    0.71
     Hwy
    0.71
     יכול
    0.71
    Act Density 0.006%

    No Known Activations