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

    Neuronpedia

    INDEX
    Explanations

    6

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    撞
    -0.09
     असर
    -0.08
    -Pierre
    -0.08
    446
    -0.08
     पड
    -0.08
     טר
    -0.08
    -playing
    -0.07
     గొ
    -0.07
     येथे
    -0.07
     интихоб
    -0.07
    POSITIVE LOGITS
     textarea
    0.09
     kategori
    0.09
    ynthesize
    0.08
     Paragraph
    0.08
     mentor
    0.08
    ประก
    0.08
    mailto
    0.08
     letras
    0.08
     keywords
    0.08
     hashtags
    0.08
    Act Density 0.003%

    No Known Activations