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

    Neuronpedia

    INDEX
    Explanations

    django imports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝚐
    0.68
    alaikums
    0.66
    रत
    0.63
     त
    0.61
     arrhythmias
    0.61
    كس
    0.61
     ત
    0.60
    爫
    0.60
    𝓃
    0.59
    开始
    0.58
    POSITIVE LOGITS
    <0x0D>
    0.97
    -
    0.89
    (
    0.78
     be
    0.77
    im
    0.76
    O
    0.74
    from
    0.73
    L
    0.73
    _
    0.72
    ↵
    0.71
    Act Density 0.007%

    No Known Activations