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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ironically
    -0.07
    ȹ
    -0.07
    وز
    -0.06
     anom
    -0.06
    �
    -0.06
    道士
    -0.06
    IGN
    -0.06
     ulus
    -0.06
    Discussion
    -0.06
    议员
    -0.06
    POSITIVE LOGITS
    	lcd
    0.08
    中文
    0.07
    洛
    0.07
    __;↵
    0.07
    (dtype
    0.07
    >.↵↵
    0.07
    _delivery
    0.07
    Esc
    0.07
     Seeking
    0.07
     Kısa
    0.07
    Act Density 0.028%

    No Known Activations