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

    Neuronpedia

    INDEX
    Explanations

    EPA

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .watch
    -0.08
     ремон
    -0.08
     Cach
    -0.07
     самых
    -0.07
    দের
    -0.07
    ప
    -0.07
     courant
    -0.07
    ক্রান্ত
    -0.07
    プロ
    -0.07
     transmit
    -0.07
    POSITIVE LOGITS
     Patti
    0.09
     fumes
    0.08
     Dennis
    0.08
    geber
    0.08
     STATIC
    0.08
    -author
    0.08
    માંથી
    0.08
    (author
    0.08
    Pid
    0.08
    Going
    0.08
    Act Density 0.003%

    No Known Activations