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

    Neuronpedia

    INDEX
    Explanations

    classified, request, decision, electrons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    m
    0.96
    n
    0.92
    k
    0.92
    p
    0.88
    ns
    0.84
    d
    0.79
    ↵↵
    0.78
     OD
    0.77
    ing
    0.77
    ن
    0.77
    POSITIVE LOGITS
     Nahrung
    0.73
    flächen
    0.68
    minLength
    0.68
     সহকারী
    0.67
    Trails
    0.65
    膀
    0.65
    ojen
    0.65
     bör
    0.64
    జ్య
    0.64
    >>();
    0.63
    Act Density 0.003%

    No Known Activations