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

    Neuronpedia

    INDEX
    Explanations

    SELECT *

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    \
    0.76
    m
    0.68
    ts
    0.65
    ال
    0.61
    ri
    0.61
    s
    0.61
    d
    0.61
    p
    0.60
    자
    0.60
    los
    0.59
    POSITIVE LOGITS
     CIRCU
    0.59
     jeopard
    0.58
     financi
    0.57
     rescu
    0.57
     Chocol
    0.56
     COLLATION
    0.55
     MANUFACTURING
    0.55
     sfâr
    0.55
     posibil
    0.55
     produc
    0.54
    Act Density 0.001%

    No Known Activations