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

    Neuronpedia

    INDEX
    Explanations

    adverbs indicating time, manner, or conditions

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

    temporal or causal conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للاسماء
    -0.78
    .*")]
    -0.67
    rungsseite
    -0.59
    awtextra
    -0.59
     المعيارى
    -0.56
     DbType
    -0.55
    ValueStyle
    -0.55
     pungkasnya
    -0.55
    antro
    -0.55
     dAtA
    -0.54
    POSITIVE LOGITS
     geliş
    0.41
     occurs
    0.39
     naturally
    0.36
    Aiheesta
    0.35
    Saiba
    0.34
     yine
    0.33
     espont
    0.33
     happens
    0.33
     occur
    0.32
    ไ
    0.32
    Act Density 0.105%

    No Known Activations