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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    StandardItem
    -0.06
    ?>'
    -0.06
     McGr
    -0.06
     vezes
    -0.06
    'A
    -0.06
     Panther
    -0.06
     FOUR
    -0.06
    Designed
    -0.06
     nuova
    -0.06
    ımızda
    -0.06
    POSITIVE LOGITS
     complementary
    0.07
     compensation
    0.07
     quen
    0.06
    calc
    0.06
     statistically
    0.06
    Demon
    0.06
    	sleep
    0.06
     台
    0.06
    áře
    0.06
    _union
    0.06
    Act Density 0.000%

    No Known Activations