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

    Neuronpedia

    INDEX
    Explanations

    foreign language characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Fast
    0.78
     Pregnancy
    0.76
    embryon
    0.76
    ottesville
    0.73
     editorials
    0.73
     alcoholism
    0.73
    ષ્ટ્ર
    0.73
    mère
    0.72
    imgur
    0.72
     trolls
    0.71
    POSITIVE LOGITS
    珥
    0.67
    ᓂ
    0.66
    साइ
    0.66
    Дру
    0.65
     धनु
    0.63
    选择
    0.63
     Mith
    0.60
    埼
    0.59
     धी
    0.58
    шении
    0.58
    Act Density 0.169%

    No Known Activations