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

    Neuronpedia

    INDEX
    Explanations

    occurrences of definite and indefinite articles along with forms of negation

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

    foreign language, programming terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :✨
    -0.46
     Himo
    -0.41
     numériques
    -0.39
     fermés
    -0.38
     navideñas
    -0.38
     sexuales
    -0.38
     fédé
    -0.37
     judiciales
    -0.35
     adjunto
    -0.35
     description
    -0.35
    POSITIVE LOGITS
     esternos
    0.68
    脚注の使い方
    0.65
    mergeFrom
    0.61
    GEBURTSDATUM
    0.58
     autorytatywna
    0.58
     propOrder
    0.58
     חיצוניים
    0.56
    principalColumn
    0.55
    AndEndTag
    0.54
    DllImport
    0.54
    Act Density 0.014%

    No Known Activations