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

    Neuronpedia

    INDEX
    Explanations

    Legal agreements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     PNG
    -0.07
    tempts
    -0.06
    .connect
    -0.06
     nuclear
    -0.06
     morality
    -0.06
    ط
    -0.06
     tax
    -0.06
    ığı
    -0.06
    äch
    -0.06
    Alright
    -0.06
    POSITIVE LOGITS
     первого
    0.07
     ड
    0.07
    .getIndex
    0.06
    색
    0.06
    (jq
    0.06
    \Db
    0.06
    .addItem
    0.06
    分析
    0.06
    自分
    0.06
    	logrus
    0.06
    Act Density 0.003%

    No Known Activations