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

    Neuronpedia

    INDEX
    Explanations

    phrases that discuss relationships or comparisons regarding quality and value

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

    Appearing before adjectives or descriptive words

    np_acts-logits-general · gemini-2.0-flash

    articles and conjunctions followed by nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ویکی‌پدی
    -0.46
     resourceCulture
    -0.45
    ArgsConstructor
    -0.42
    Ƚ
    -0.42
    rungsseite
    -0.41
    RefNanny
    -0.40
    CodedInputStream
    -0.40
    gtest
    -0.39
     OkHttpClient
    -0.39
    msford
    -0.36
    POSITIVE LOGITS
    󠁢
    0.63
     autorytatywna
    0.51
    下载附件
    0.50
     defaultstate
    0.46
    setof
    0.45
    SequentialGroup
    0.45
    BagConstraints
    0.45
    期刊论文
    0.43
    UnsafeEnabled
    0.42
    不愧
    0.42
    Act Density 0.369%

    No Known Activations