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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     interviews
    -0.06
     بلغ
    -0.06
    .Doc
    -0.06
     برنامه
    -0.06
     extremes
    -0.06
    กรรมการ
    -0.06
    展示
    -0.06
    withstanding
    -0.06
     nad
    -0.06
     coalition
    -0.06
    POSITIVE LOGITS
     Fool
    0.07
    ebe
    0.07
    Under
    0.06
    _MISS
    0.06
    (Sender
    0.06
    setUp
    0.06
     amateur
    0.06
     posY
    0.06
     Sharp
    0.06
    .↵↵
    0.06
    Act Density 0.074%

    No Known Activations