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

    Neuronpedia

    INDEX
    Explanations

    multiple languages, greetings, offers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    uretic
    0.31
    ittances
    0.30
     recognises
    0.28
    rategy
    0.27
    geoning
    0.27
    onomous
    0.26
    atorship
    0.26
     realises
    0.26
    iconductor
    0.26
    ষুধ
    0.26
    POSITIVE LOGITS
     タイ
    0.24
     என்ற
    0.24
     書
    0.23
     張
    0.23
    ிய
    0.23
    ¹
    0.23
    λ
    0.22
    Ade
    0.22
    See
    0.22
     ジョ
    0.22
    Act Density 0.000%

    No Known Activations