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

    Neuronpedia

    INDEX
    Explanations

    7

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Cumhur
    -0.07
    ono
    -0.07
    uf
    -0.07
     dus
    -0.07
    unt
    -0.07
     Was
    -0.07
    Mis
    -0.06
     Zum
    -0.06
     Consort
    -0.06
     wenig
    -0.06
    POSITIVE LOGITS
    公示
    0.07
    .arrow
    0.07
    сел
    0.07
    	char
    0.07
    两千
    0.07
    /YYYY
    0.07
    	INNER
    0.07
     UPPER
    0.07
    _passed
    0.07
     населения
    0.07
    Act Density 0.001%

    No Known Activations