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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     skips
    -0.07
    	dd
    -0.06
    isVisible
    -0.06
     Division
    -0.06
    .Destroy
    -0.06
    ็นผ
    -0.06
     padd
    -0.06
    culated
    -0.06
    OOM
    -0.06
    rb
    -0.06
    POSITIVE LOGITS
     образования
    0.07
     Ergebn
    0.06
     dive
    0.06
     tầm
    0.06
     요구
    0.06
     совет
    0.06
     گزارش
    0.06
     строитель
    0.06
     quan
    0.06
     важ
    0.06
    Act Density 0.000%

    No Known Activations