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

    Neuronpedia

    INDEX
    Explanations

    LaTeX tikz and utf8 encoding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    дьми
    0.36
     युव
    0.36
     কূটনীতিক
    0.35
     कम्पनी
    0.34
     साम्रा
    0.34
    रुख
    0.33
    兒
    0.33
    ัพท์
    0.33
    Yard
    0.33
    केंसी
    0.33
    POSITIVE LOGITS
    o
    0.31
    به
    0.31
    λ
    0.30
     Pais
    0.29
    ὀ
    0.29
    không
    0.29
    toCharArray
    0.29
     χρήση
    0.29
    en
    0.29
    不超过
    0.29
    Act Density 0.000%

    No Known Activations