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

    Neuronpedia

    INDEX
    Explanations

    class

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    __),
    -0.06
    عر
    -0.06
    elts
    -0.06
    ENU
    -0.06
    Tre
    -0.06
    echan
    -0.06
    _pick
    -0.06
     JUST
    -0.06
    няет
    -0.06
    ΑΘ
    -0.06
    POSITIVE LOGITS
     BadRequest
    0.07
     выход
    0.07
    市
    0.07
     вий
    0.06
    upportInitialize
    0.06
    (Base
    0.06
    ................................
    0.06
    ковые
    0.06
    vector
    0.06
    .EVT
    0.06
    Act Density 0.020%

    No Known Activations