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

    Neuronpedia

    INDEX
    Explanations

    et

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.08
    馝
    -0.07
    итесь
    -0.07
     Bytes
    -0.07
    Represent
    -0.07
    辉煌
    -0.07
    blog
    -0.07
    我喜欢
    -0.06
    qry
    -0.06
    oord
    -0.06
    POSITIVE LOGITS
    acı
    0.08
    elastic
    0.07
    (container
    0.07
    /*.
    0.07
     rescued
    0.07
    Uluslararası
    0.07
     accusing
    0.07
    ----------
↵
    0.07
     orchestrated
    0.07
     Abel
    0.07
    Act Density 0.001%

    No Known Activations