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

    Neuronpedia

    INDEX
    Explanations

    comment and documentation block indicators in code

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

    section separators or headings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Italijanski
    -0.95
    parsedMessage
    -0.89
     незавершена
    -0.89
     Chwiliwch
    -0.89
    twimg
    -0.87
     Taktlose
    -0.87
     ویکی‌پدی
    -0.86
     transfieras
    -0.84
    usercontent
    -0.77
     zwiſchen
    -0.75
    POSITIVE LOGITS
    ↵↵
    0.53
    .
    0.47
    :
    0.46
        
    0.45
    endregion
    0.43
    1
    0.43
    先
    0.41
     if
    0.41
     Part
    0.41
     First
    0.40
    Act Density 0.040%

    No Known Activations