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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    CAA
    -0.07
    ком
    -0.06
    madan
    -0.06
    runner
    -0.06
    ertia
    -0.06
    GENCY
    -0.06
     heel
    -0.06
     cos
    -0.06
     cocci
    -0.06
     occurring
    -0.05
    POSITIVE LOGITS
    ;"
    0.07
    бе
    0.07
    	fill
    0.07
     官
    0.07
     счит
    0.07
     Sync
    0.07
     الإسلام
    0.06
    (SE
    0.06
    888
    0.06
     loser
    0.06
    Act Density 0.166%

    No Known Activations