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

    Neuronpedia

    INDEX
    Explanations

    examples of book titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    事物
    0.72
     hairs
    0.63
    意思
    0.60
     nigg
    0.60
     granules
    0.59
    ب
    0.59
    د
    0.59
     mouthful
    0.59
     attractor
    0.58
    𝕥
    0.58
    POSITIVE LOGITS
    books
    0.57
    त
    0.54
     वर्षे
    0.54
    worms
    0.51
    เทศ
    0.51
    логов
    0.51
    buch
    0.50
    reihe
    0.50
    Ο
    0.50
    Azer
    0.50
    Act Density 0.188%

    No Known Activations