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

    Neuronpedia

    INDEX
    Explanations

    showing equivalence to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ह
    0.79
    the
    0.73
    4
    0.72
    ка
    0.71
    c
    0.71
    h
    0.69
    EY
    0.68
    a
    0.68
    $
    0.67
    Have
    0.67
    POSITIVE LOGITS
     enunciado
    0.63
    zám
    0.63
    ம்
    0.62
     кни
    0.59
    íme
    0.58
     OpenCV
    0.58
     indistinct
    0.58
    石头
    0.58
    ర
    0.57
    洴
    0.57
    Act Density 0.001%

    No Known Activations