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

    Neuronpedia

    INDEX
    Explanations

    compare

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sr
    -0.07
    uintptr
    -0.07
     tisí
    -0.06
    -notes
    -0.06
    ılış
    -0.06
    -health
    -0.06
     wat
    -0.06
     Ranked
    -0.06
     DEVELO
    -0.06
    298
    -0.06
    POSITIVE LOGITS
    .amazon
    0.06
     فول
    0.06
    itant
    0.06
     oldukça
    0.06
    .yellow
    0.06
    око
    0.06
    _ASSERT
    0.06
     comparing
    0.06
     나
    0.06
    ={{↵
    0.06
    Act Density 0.014%

    No Known Activations