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

    Neuronpedia

    INDEX
    Explanations

    data structure dimensions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    t
    0.77
    f
    0.70
    ي
    0.68
    z
    0.66
    or
    0.63
    op
    0.61
    ses
    0.61
    اپ
    0.61
    וש
    0.60
    ונה
    0.59
    POSITIVE LOGITS
     acero
    0.67
    Leben
    0.61
     energía
    0.59
    ?
    0.59
    의
    0.59
    Metal
    0.58
    Nature
    0.58
    2
    0.58
    LM
    0.57
    Gas
    0.57
    Act Density 0.010%

    No Known Activations