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

    Neuronpedia

    INDEX
    Explanations

    aspects related to commentary and feedback around various subjects

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

    explanation and description

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Portail
    -0.63
     wireType
    -0.58
     للاسماء
    -0.58
    transQ
    -0.56
     '\\;'
    -0.54
     فريبيس
    -0.52
    EndInit
    -0.52
    drawSprites
    -0.50
    AndEndTag
    -0.49
    enderror
    -0.48
    POSITIVE LOGITS
     explanations
    0.94
     accompanying
    0.92
     descriptions
    0.92
     commentary
    0.90
     explanatory
    0.89
     explanation
    0.87
     description
    0.85
     explicación
    0.82
     explaining
    0.80
     설명
    0.79
    Act Density 0.066%

    No Known Activations