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

    Neuronpedia

    INDEX
    Explanations

    numbers and math symbols

    oai_token-act-pair · gemini-2.0-flash

    Calculations and equations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     оригіналу
    -0.52
     Six
    -0.49
    六
    -0.46
    6
    -0.42
    št
    -0.42
    mann
    -0.42
    бурга
    -0.42
    2
    -0.41
    ContentValues
    -0.41
     Sixty
    -0.41
    POSITIVE LOGITS
    errHandler
    0.65
     Мексичка
    0.61
    hassee
    0.60
     Italijanski
    0.58
     Fourteenth
    0.57
     Wikispecies
    0.57
    WriteBarrier
    0.56
    milan
    0.56
     fourth
    0.56
    Autoritní
    0.56
    Act Density 1.480%

    No Known Activations