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

    Neuronpedia

    INDEX
    Explanations

    specialized code syntax and formatting elements

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

    Code, math, or unusual symbols

    np_acts-logits-general · gemini-2.0-flash

    code and special characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    &#
    -0.60
     &#
    -0.50
     even
    -0.49
    cein
    -0.49
    iden
    -0.47
    ֵל
    -0.46
    arakat
    -0.46
     also
    -0.46
    뀜
    -0.45
     I
    -0.44
    POSITIVE LOGITS
     للاسماء
    0.91
     typelib
    0.84
     ​​
    0.82
     الرياضيه
    0.82
    Hozzáférés
    0.80
     الحره
    0.80
     resourceCulture
    0.79
    __":
    0.79
    __':
    0.79
    ագրություններ
    0.78
    Act Density 0.325%

    No Known Activations