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

    Neuronpedia

    INDEX
    Explanations

    3

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lectures
    -0.08
     crisis
    -0.07
     Fórum
    -0.07
     (?)
    -0.07
    _rule
    -0.07
    motiv
    -0.07
     İ
    -0.07
    fp
    -0.07
     Harris
    -0.07
    Applet
    -0.07
    POSITIVE LOGITS
     สลาก
    0.09
    <|constrain|>
    0.08
    	log
    0.08
    უთხ
    0.08
    сияи
    0.08
     acknowledgment
    0.08
    იობ
    0.08
    აუბ
    0.08
    ไทยฟรี
    0.08
    	reg
    0.08
    Act Density 0.002%

    No Known Activations