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

    Neuronpedia

    INDEX
    Explanations

    news and media citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ogenic
    0.82
    的信息
    0.80
     Pills
    0.80
     pages
    0.79
    信息的
    0.78
    ‌های
    0.77
    ඪ
    0.77
     stupidity
    0.77
    库存
    0.76
    おり
    0.76
    POSITIVE LOGITS
    /
    0.69
     latina
    0.65
    ัด
    0.63
    Composer
    0.62
    hombre
    0.61
     devrez
    0.60
     gấp
    0.60
     চাঁ
    0.59
     asked
    0.59
     interpreta
    0.59
    Act Density 0.060%

    No Known Activations