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

    Neuronpedia

    INDEX
    Explanations

    code and web elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     onderdeel
    0.53
    TikTok
    0.49
    HY
    0.49
    set
    0.49
     classic
    0.48
     طی
    0.48
    Classic
    0.47
     nostalgic
    0.47
    JP
    0.47
     strong
    0.46
    POSITIVE LOGITS
     trypsin
    0.56
    ικη
    0.55
    𒁺
    0.55
    仙台
    0.54
    ྔ
    0.54
     Centres
    0.52
    <unused493>
    0.51
     Pleistocene
    0.51
    خن
    0.51
     acetonitrile
    0.51
    Act Density 0.034%

    No Known Activations