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

    Neuronpedia

    INDEX
    Explanations

    key phrases or references to studies, specifically mentioning quantities or comparative phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    description of a series

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Administrativna
    -0.72
    GEBURTSDATUM
    -0.71
     propOrder
    -0.65
    Personendaten
    -0.61
    帖最后由
    -0.60
     utafitiHapana
    -0.56
     незавершена
    -0.54
     Privacidade
    -0.54
     autorytatywna
    -0.54
    ьаж
    -0.53
    POSITIVE LOGITS
    tagHelperRunner
    0.45
     aldea
    0.31
    IBLES
    0.29
     pañ
    0.29
    tanleria
    0.29
    tocks
    0.28
    bbene
    0.28
    odine
    0.28
     grecque
    0.28
     scolaires
    0.28
    Act Density 0.016%

    No Known Activations