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

    Neuronpedia

    INDEX
    Explanations

    punctuations and symbols within the text

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

    modify orORoror

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ویکی‌پدی
    -0.48
    المكان
    -0.47
     بيها
    -0.47
     GenerationType
    -0.45
     Normdatei
    -0.44
    elemField
    -0.39
     defaultstate
    -0.38
    годня
    -0.38
    tanleria
    -0.38
     мәкал
    -0.37
    POSITIVE LOGITS
     or
    0.57
     any
    0.53
     Qualquer
    0.47
    이나
    0.47
     quaisquer
    0.46
    หรือ
    0.44
     qualquer
    0.44
     insurance
    0.44
     Any
    0.43
     security
    0.43
    Act Density 0.058%

    No Known Activations