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

    Neuronpedia

    INDEX
    Explanations

    math symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     MSG
    -0.08
     thick
    -0.07
     catastrophe
    -0.07
     reliable
    -0.07
     zuverlässig
    -0.07
     подобрать
    -0.07
     differenti
    -0.07
     مام
    -0.07
     הבח
    -0.07
    ight
    -0.07
    POSITIVE LOGITS
     ratios
    0.09
    ताओं
    0.08
     minuto
    0.08
    Pointers
    0.08
     comparing
    0.08
    الی
    0.08
    !=(
    0.08
     escreveu
    0.08
     Pointer
    0.08
     Compare
    0.08
    Act Density 0.038%

    No Known Activations