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

    Neuronpedia

    INDEX
    Explanations

    non-english words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     alphanumeric
    0.39
     hyperparameters
    0.35
     চালু
    0.35
     photonic
    0.35
    مثل
    0.34
    ڎ
    0.34
     geochemical
    0.34
    ضافة
    0.34
    Ⴖ
    0.33
     infographics
    0.33
    POSITIVE LOGITS
    ani
    0.36
    ata
    0.35
    on
    0.34
    as
    0.34
    it
    0.33
    ot
    0.33
    an
    0.32
    at
    0.31
    ar
    0.31
    ter
    0.31
    Act Density 0.033%

    No Known Activations