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

    Neuronpedia

    INDEX
    Explanations

    target

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rade
    -0.07
    十一
    -0.06
    _open
    -0.06
     apresent
    -0.06
     جشن
    -0.06
    chn
    -0.06
    ối
    -0.06
    قق
    -0.06
    /reset
    -0.06
     nuevo
    -0.06
    POSITIVE LOGITS
     AIR
    0.06
    leground
    0.06
    Prosec
    0.06
     vampire
    0.06
     COURT
    0.06
     Reds
    0.06
    """↵↵↵
    0.06
     Anatomy
    0.06
     BASIS
    0.06
    Elect
    0.06
    Act Density 0.013%

    No Known Activations