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

    Neuronpedia

    INDEX
    Explanations

    curve

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     स्रोत
    -0.08
     उत्स
    -0.07
     contributors
    -0.07
     highways
    -0.07
     volunteer
    -0.07
     abc
    -0.07
     contributor
    -0.07
     yan
    -0.07
     volunteering
    -0.07
     basalt
    -0.07
    POSITIVE LOGITS
     piis
    0.09
    诈骗
    0.08
    тически
    0.08
     efectivo
    0.08
     спр
    0.08
    цо
    0.08
    骗
    0.08
    ódigo
    0.08
    ístico
    0.08
    Serie
    0.08
    Act Density 0.003%

    No Known Activations