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

    Neuronpedia

    INDEX
    Explanations

    numerical sequences and fractions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Render
    0.68
    Barrier
    0.65
    abody
    0.63
    base
    0.63
    ตัว
    0.62
     Restoration
    0.61
    minIndex
    0.61
     सेवानिव
    0.61
     دیکھنے
    0.61
     EnglishChoose
    0.60
    POSITIVE LOGITS
     po
    0.82
     Po
    0.71
     erop
    0.69
     попа
    0.69
     नार
    0.69
    po
    0.67
    خي
    0.66
    トー
    0.65
    ेक
    0.63
     log
    0.63
    Act Density 0.010%

    No Known Activations