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

    Neuronpedia

    INDEX
    Explanations

    get your

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     agrav
    1.23
     católica
    1.21
    ็ต
    1.18
    儁
    1.15
     моя
    1.14
     tequila
    1.13
     mismos
    1.13
     jose
    1.12
     هات
    1.10
    aucune
    1.08
    POSITIVE LOGITS
    ();}
    1.33
    ي
    1.23
     шту
    1.22
    くまで
    1.21
    y
    1.20
    ationale
    1.19
    ന്
    1.18
    ൻ
    1.17
    Verlag
    1.17
    i
    1.17
    Act Density 0.001%

    No Known Activations