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

    Neuronpedia

    INDEX
    Explanations

    code and formulas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Nunes
    -0.06
     Zelda
    -0.06
    <IEnumerable
    -0.06
     rainbow
    -0.06
     Зав
    -0.06
    “As
    -0.06
     Spielberg
    -0.06
     çal
    -0.06
    (proto
    -0.06
     putchar
    -0.06
    POSITIVE LOGITS
     di
    0.07
    47
    0.06
     veterans
    0.06
     Passed
    0.06
     pri
    0.06
    这里
    0.06
     injections
    0.06
     bgcolor
    0.06
     방법
    0.06
     detailed
    0.06
    Act Density 0.000%

    No Known Activations