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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or specific names in the text

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

    Gerhard and associated names/titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    -0.94
    URLException
    -0.58
    ים
    -0.58
    stylesheet
    -0.56
    تفصیلات
    -0.52
     Verhält
    -0.48
     soñ
    -0.48
     chrétien
    -0.47
    tım
    -0.47
    😂😂😂
    -0.47
    POSITIVE LOGITS
    y
    0.82
    <bos>
    0.65
    ي
    0.64
    al
    0.61
    ان
    0.56
    ️
    0.50
    %)$
    0.49
    й
    0.49
    י
    0.47
    ic
    0.47
    Act Density 0.409%

    No Known Activations