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

    Neuronpedia

    INDEX
    Explanations

    mut

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    orca
    -0.06
    ackers
    -0.06
     kuzey
    -0.06
     Thumbnail
    -0.06
    emed
    -0.06
    ня
    -0.06
     Vương
    -0.06
    _AT
    -0.06
     Sponsor
    -0.06
    .attachment
    -0.06
    POSITIVE LOGITS
    后的
    0.07
     very
    0.07
     bot
    0.07
     pupils
    0.06
    最后
    0.06
     websocket
    0.06
     nejd
    0.06
     UART
    0.06
    CLE
    0.06
     руки
    0.06
    Act Density 0.006%

    No Known Activations