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

    Neuronpedia

    INDEX
    Explanations

    listing quantities and items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ون
    0.76
    ار
    0.74
    िंग
    0.70
    ić
    0.65
    कालीन
    0.64
    ح
    0.63
    ैम
    0.61
    aną
    0.61
     Epile
    0.61
    es
    0.60
    POSITIVE LOGITS
    0
    0.99
    _
    0.77
    .
    0.73
    S
    0.69
    LIST
    0.63
    B
    0.63
    Q
    0.63
     burung
    0.63
    İ
    0.62
    ﺭ
    0.62
    Act Density 0.075%

    No Known Activations