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

    Neuronpedia

    INDEX
    Explanations

    key-value pairs and structured data representations

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

    hexadecimal numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MessageOf
    -0.91
    parsedMessage
    -0.84
     Савезне
    -0.82
    setVerticalGroup
    -0.78
     betweenstory
    -0.74
     pouvoit
    -0.73
    oredCriteria
    -0.73
     '\\;'
    -0.70
     Geſch
    -0.69
    dafx
    -0.68
    POSITIVE LOGITS
     sign
    0.30
    合
    0.29
     h
    0.29
     
    0.29
     =
    0.29
    </em>
    0.28
     tal
    0.28
     certain
    0.27
    </i>
    0.27
     $
    0.26
    Act Density 0.166%

    No Known Activations