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

    Neuronpedia

    INDEX
    Explanations

    permutations calculation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     moeten
    -0.09
     wichtigsten
    -0.09
     بودن
    -0.09
     شدن
    -0.08
    ிலையில்
    -0.08
    mí
    -0.08
    ="\
    -0.08
     волн
    -0.08
     geti
    -0.08
     worried
    -0.07
    POSITIVE LOGITS
     factorial
    0.09
    .$$
    0.07
     vej
    0.07
     בע
    0.07
     Ign
    0.07
     Vaugh
    0.07
    ovirus
    0.07
    ovir
    0.07
     ग्राह
    0.07
     सम
    0.07
    Act Density 0.039%

    No Known Activations