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

    Neuronpedia

    INDEX
    Explanations

    specialized terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     مستقل
    0.39
     پیشہ
    0.39
    })-(\
    0.38
     checkIf
    0.37
    OLINA
    0.37
    +}\
    0.37
     বিশ্লেষণের
    0.37
    ଙ
    0.36
    +}$
    0.36
    んど
    0.36
    POSITIVE LOGITS
     Music
    0.45
     musically
    0.44
    默
    0.42
     Sor
    0.42
     musica
    0.42
    Music
    0.42
     Musik
    0.41
    Cate
    0.38
     McCain
    0.38
     Blas
    0.38
    Act Density 0.000%

    No Known Activations