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

    Neuronpedia

    INDEX
    Explanations

    you

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Loft
    -0.07
     маст
    -0.06
    솔
    -0.06
     oldukları
    -0.06
    ủi
    -0.06
     compartments
    -0.06
     Pluto
    -0.06
     ль
    -0.06
    仲
    -0.06
    UnderTest
    -0.06
    POSITIVE LOGITS
     науч
    0.07
    ятель
    0.07
     Cir
    0.06
    TT
    0.06
     fizik
    0.06
    score
    0.06
     fieldName
    0.06
    boys
    0.06
    .remove
    0.06
    /gen
    0.06
    Act Density 0.013%

    No Known Activations