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

    Neuronpedia

    INDEX
    Explanations

    take

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     metal
    -0.07
     negatives
    -0.06
     columnist
    -0.06
    issa
    -0.06
     Sleep
    -0.06
     faucet
    -0.06
     inconsistent
    -0.06
    찌
    -0.06
     supervisor
    -0.06
     surrounding
    -0.06
    POSITIVE LOGITS
    ाव
    0.06
    manı
    0.06
     꼭
    0.06
     endforeach
    0.06
     coeff
    0.06
     ней
    0.06
     ofType
    0.06
    нов
    0.06
    imming
    0.06
    	PORT
    0.06
    Act Density 0.074%

    No Known Activations