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

    Neuronpedia

    INDEX
    Explanations

    numbers and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     der
    0.45
     yani
    0.45
    ہ
    0.44
     corps
    0.44
     interim
    0.43
    kowe
    0.43
    ರೋ
    0.42
     Interim
    0.42
     urbano
    0.41
    0.41
    POSITIVE LOGITS
    getRepository
    0.50
     سپورت
    0.45
    QX
    0.44
    ৤
    0.43
     ля
    0.43
    webm
    0.43
    nonpayable
    0.43
     markedly
    0.42
     திரைப்படம்
    0.42
    펫
    0.42
    Act Density 0.003%

    No Known Activations