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

    Neuronpedia

    INDEX
    Explanations

    formal qualities and specifics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     to
    2.42
     on
    2.38
    ل
    1.63
    1
    1.63
     at
    1.57
     with
    1.41
    ב
    1.36
    ル
    1.33
     and
    1.29
     or
    1.29
    POSITIVE LOGITS
    :
    1.70
    ي
    1.66
    يته
    1.27
     opération
    1.25
    يها
    1.25
    يلا
    1.25
    توى
    1.24
     expérience
    1.21
    يلي
    1.16
     étude
    1.16
    Act Density 0.310%

    No Known Activations