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

    Neuronpedia

    INDEX
    Explanations

    punctuation and formatting elements typically used in structured data or code

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

    C-style bitfields

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Microsoft
    -0.40
     Microsoft
    -0.40
     fast
    -0.36
     Hall
    -0.35
    DIRECT
    -0.34
    fast
    -0.33
    ErrorException
    -0.33
     برانيه
    -0.32
     our
    -0.32
    Fast
    -0.31
    POSITIVE LOGITS
    parsedMessage
    1.09
    windowFixed
    0.83
    ValueStyle
    0.79
     Савезне
    0.79
     nahilalakip
    0.78
    expandindo
    0.76
     يتيمه
    0.76
    ftagPool
    0.76
    rungsseite
    0.75
     CanadaChoose
    0.75
    Act Density 0.000%

    No Known Activations