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

    Neuronpedia

    INDEX
    Explanations

    common functional words and phrases in sentences

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

    repeated common words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -0.66
    UrlResolution
    -0.58
     arşivlendi
    -0.58
    󠁣
    -0.57
    Personensuche
    -0.57
    AnchorTagHelper
    -0.56
     JpaRepository
    -0.54
    featureID
    -0.54
     мәкал
    -0.53
    +#+#
    -0.51
    POSITIVE LOGITS
    Yess
    0.51
     Nieren
    0.49
     Leopoldo
    0.49
     Motta
    0.47
     Snow
    0.46
     Delgado
    0.46
     snows
    0.45
     bizarre
    0.45
     snow
    0.45
     bab
    0.44
    Act Density 0.146%

    No Known Activations