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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     دار
    -0.06
    ﺘ
    -0.06
    ραν
    -0.06
     поки
    -0.06
     tackles
    -0.06
     použít
    -0.06
     yapmak
    -0.06
     풀
    -0.06
    PP
    -0.06
    레벨
    -0.06
    POSITIVE LOGITS
     curator
    0.07
    inx
    0.07
    enas
    0.06
    }],
    0.06
    ator
    0.06
    edian
    0.06
     pct
    0.06
     �
    0.06
     Democrat
    0.06
    inte
    0.06
    Act Density 0.016%

    No Known Activations