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

    Neuronpedia

    INDEX
    Explanations

    help/

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     head
    0.79
     heads
    0.68
     divisor
    0.68
    atelle
    0.66
     HEAD
    0.65
     disenfranch
    0.62
    head
    0.62
     كوب
    0.62
    headed
    0.61
    सीसीआई
    0.60
    POSITIVE LOGITS
    अस
    0.67
    ंख
    0.65
    निया
    0.62
    须
    0.59
    Trail
    0.58
     الجام
    0.58
    Golden
    0.57
    Tur
    0.56
    ナ
    0.55
     గా
    0.55
    Act Density 0.045%

    No Known Activations