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

    Neuronpedia

    INDEX
    Explanations

    common pronouns and articles in various languages

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

    German, danish, french, spanish pronouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.57
     tartalomajánló
    -0.54
     kasarigan
    -0.53
     warfare
    -0.40
    出版年
    -0.39
     للاسماء
    -0.37
    isalpha
    -0.37
    bootstrapcdn
    -0.36
     BrowserModule
    -0.36
    stylesheet
    -0.36
    POSITIVE LOGITS
     mereka
    0.74
     Mereka
    0.69
     they
    0.68
    mereka
    0.65
     они
    0.64
    Mereka
    0.63
     theyre
    0.63
    他們
    0.61
     ellos
    0.61
    他们
    0.61
    Act Density 0.001%

    No Known Activations