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

    Neuronpedia

    INDEX
    Explanations

    drive

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    丈夫
    -0.06
     labeled
    -0.06
    _VISIBLE
    -0.06
     tofu
    -0.06
     Chiefs
    -0.06
    anj
    -0.06
    óż
    -0.06
     suffix
    -0.06
     Faculty
    -0.06
    реж
    -0.06
    POSITIVE LOGITS
    platz
    0.07
     первой
    0.06
     kindness
    0.06
    À
    0.06
    //--------------------------------------------------------------↵
    0.06
     المس
    0.06
    590
    0.06
     rund
    0.06
    -prev
    0.06
     advance
    0.06
    Act Density 0.007%

    No Known Activations