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

    Neuronpedia

    INDEX
    Explanations

    Faul

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     osób
    -0.07
     discussed
    -0.06
    .flat
    -0.06
     инструк
    -0.06
     fullname
    -0.06
     registers
    -0.06
    RESULTS
    -0.06
    OOD
    -0.06
     çoğu
    -0.06
    	free
    -0.06
    POSITIVE LOGITS
     Caul
    0.08
     Saul
    0.08
    aul
    0.07
    ULK
    0.07
     Maul
    0.07
     Braun
    0.07
     Faul
    0.07
     Reaper
    0.07
     Kingdom
    0.06
     caul
    0.06
    Act Density 0.003%

    No Known Activations