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

    Neuronpedia

    INDEX
    Explanations

    link to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    f
    0.71
    t
    0.71
    j
    0.68
    ad
    0.68
    <0x80>
    0.64
    q
    0.64
    is
    0.63
    0
    0.63
    h
    0.62
    يس
    0.61
    POSITIVE LOGITS
     link
    0.95
    م
    0.93
     links
    0.89
    links
    0.79
    链接
    0.79
     ties
    0.79
    Link
    0.79
    เชื่อม
    0.78
    link
    0.77
     hyperlinks
    0.77
    Act Density 0.030%

    No Known Activations