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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     scratched
    -0.07
     bizi
    -0.06
     expresses
    -0.06
     Parks
    -0.06
    .Players
    -0.06
    oyo
    -0.06
    adil
    -0.06
    neg
    -0.06
     tři
    -0.06
    ักส
    -0.06
    POSITIVE LOGITS
    ()</
    0.06
    experiment
    0.06
     THEM
    0.06
     UIG
    0.06
    (Func
    0.06
     Insider
    0.06
     Міністер
    0.06
     squarely
    0.06
     Opport
    0.06
     ।↵
    0.06
    Act Density 0.000%

    No Known Activations