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

    Neuronpedia

    INDEX
    Explanations

    references to the English language and its usage

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

    english or english wikipedia

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.63
    oa̍t
    -0.62
    httphttps
    -0.57
     استنادى
    -0.57
    بوابة
    -0.55
    
    -0.54
    󠁢
    -0.54
    tonode
    -0.53
    AndEndTag
    -0.53
    ⤹
    -0.51
    POSITIVE LOGITS
    英語
    0.46
     inglês
    0.42
     英語
    0.42
     englisch
    0.41
     English
    0.41
    heits
    0.38
     international
    0.38
    English
    0.37
     english
    0.37
     انگلیسی
    0.36
    Act Density 0.024%

    No Known Activations