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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating comprehension or acknowledgment of individual perspectives and social issues

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

    user questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    harapkan
    -0.53
     betweenstory
    -0.47
     techniczne
    -0.46
     grieved
    -0.43
     Ziegler
    -0.43
     Cahill
    -0.43
     Goldstein
    -0.43
    menea
    -0.42
    eseorang
    -0.42
    !("{}",
    -0.42
    POSITIVE LOGITS
    تقاوى
    1.02
    parsedMessage
    0.99
     незавершена
    0.97
    tagHelperRunner
    0.95
     informée
    0.94
     lenker
    0.93
    хьтан
    0.91
     autorytatywna
    0.90
     Мексичка
    0.89
     الرياضيه
    0.87
    Act Density 0.000%

    No Known Activations