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

    Neuronpedia

    INDEX
    Explanations

    order

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    +self
    -0.06
    廷
    -0.06
     glo
    -0.06
    YC
    -0.06
    科
    -0.06
     coffee
    -0.06
    cház
    -0.06
    Pří
    -0.06
     Ле
    -0.06
     trotz
    -0.06
    POSITIVE LOGITS
     amacıyla
    0.06
    unding
    0.06
     Supplement
    0.06
    ividual
    0.06
    Пер
    0.06
    PLY
    0.06
     ByteBuffer
    0.06
    InputLabel
    0.06
    UPS
    0.06
    арод
    0.06
    Act Density 0.011%

    No Known Activations