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

    Neuronpedia

    INDEX
    Explanations

    up to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     كتاب
    0.40
    Undefined
    0.39
    ອບ
    0.38
    يع
    0.38
     Computed
    0.37
    עי
    0.37
    一番
    0.37
    ोप
    0.37
    الب
    0.36
    نې
    0.36
    POSITIVE LOGITS
    welling
    0.72
    daten
    0.71
    cycled
    0.68
    dat
    0.68
    stairs
    0.66
    graded
    0.65
    stream
    0.64
    rooted
    0.63
    strokes
    0.61
     tempo
    0.60
    Act Density 0.032%

    No Known Activations