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

    Neuronpedia

    INDEX
    Explanations

    pencil and its use

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    व
    1.13
    ف
    1.02
    .
    0.88
    ка
    0.85
    다
    0.84
    dan
    0.82
    δι
    0.82
    त्
    0.81
    ام
    0.79
    دی
    0.78
    POSITIVE LOGITS
    ON
    1.09
     pencil
    1.09
     Pencil
    0.98
     láp
    0.95
    il
    0.85
    AS
    0.84
    ✏
    0.84
    is
    0.84
     pudo
    0.80
     technisch
    0.78
    Act Density 0.002%

    No Known Activations