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

    Neuronpedia

    INDEX
    Explanations

    payment card methods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ’
    0.80
    ="
    0.63
    ing
    0.60
    d
    0.60
    bly
    0.59
    pyrimidine
    0.57
    _
    0.57
    ch
    0.56
     trạng
    0.56
    绿
    0.55
    POSITIVE LOGITS
    งิน
    0.71
     invoices
    0.70
     todas
    0.70
    DBES
    0.70
     Citibank
    0.70
    ⠿
    0.70
    ショット
    0.69
     Naira
    0.67
     lira
    0.66
     웃
    0.66
    Act Density 0.028%

    No Known Activations