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

    Neuronpedia

    INDEX
    Explanations

    comma/bracket

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    홀
    -0.08
     данные
    -0.07
    sätze
    -0.07
    叇
    -0.07
    ጥ
    -0.07
    יין
    -0.07
    xls
    -0.07
     Güncelleme
    -0.07
    ᠡ
    -0.07
     hợ
    -0.07
    POSITIVE LOGITS
    did
    0.07
    _allowed
    0.07
     Kiss
    0.07
    ад
    0.07
    ding
    0.07
    �
    0.07
    ACH
    0.07
    requested
    0.07
     зад
    0.06
    ват
    0.06
    Act Density 0.033%

    No Known Activations