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

    Neuronpedia

    INDEX
    Explanations

    terms like brother-in-law

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Cher
    0.67
     \
    0.62
     But
    0.59
    ⊰
    0.58
     Rowling
    0.57
     Roan
    0.57
     Chern
    0.57
     Donnelly
    0.56
     Chen
    0.55
     Charlotte
    0.54
    POSITIVE LOGITS
    a
    0.78
    ق
    0.69
    ٹ
    0.67
    ڈی
    0.62
    ك
    0.61
    پ
    0.59
     elevated
    0.58
     perfused
    0.58
    ત્ર
    0.57
    ने
    0.56
    Act Density 0.000%

    No Known Activations