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

    Neuronpedia

    INDEX
    Explanations

    your name or reply

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ০
    1.54
    𝐑
    1.34
    aos
    1.30
    스
    1.27
    喈
    1.22
    任意の
    1.21
    handlebars
    1.19
    orders
    1.18
    𝐃
    1.18
    ס
    1.17
    POSITIVE LOGITS
    ности
    1.43
    ları
    1.40
     ಏನು
    1.35
     celebr
    1.27
    ó
    1.23
     VALID
    1.20
    ای
    1.20
     advertisement
    1.20
    没了
    1.19
    서
    1.19
    Act Density 0.307%

    No Known Activations