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

    Neuronpedia

    INDEX
    Explanations

    Alt/Option

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     μορ
    -0.09
     στο
    -0.09
     είναι
    -0.09
    atische
    -0.08
     Cardinal
    -0.08
     το
    -0.08
     në
    -0.08
    Π
    -0.08
     természet
    -0.08
     Però
    -0.08
    POSITIVE LOGITS
     clever
    0.07
     recommendations
    0.07
     extension
    0.07
     rearr
    0.07
     re
    0.07
     medications
    0.07
     Zhang
    0.07
     astrology
    0.07
     pyr
    0.07
     interc
    0.06
    Act Density 0.001%

    No Known Activations