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

    Neuronpedia

    INDEX
    Explanations

    saving five

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     implementations
    0.47
     реализации
    0.47
     অপমান
    0.46
     nirv
    0.46
    ख्ती
    0.46
     uninter
    0.45
     inappropriate
    0.43
    listOf
    0.43
     epsilon
    0.43
     불편
    0.43
    POSITIVE LOGITS
    ський
    0.47
    _
    0.46
    Fer
    0.44
    nyk
    0.42
    isy
    0.42
    za
    0.41
    inen
    0.41
     destac
    0.40
     senden
    0.40
    ystore
    0.40
    Act Density 0.003%

    No Known Activations