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

    Neuronpedia

    INDEX
    Explanations

    underscores and hyphens in code or data structures

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

    cell data or STAT

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     červená
    -0.40
    AnchorTagHelper
    -0.38
    Filmografia
    -0.34
     clearColor
    -0.32
     heapq
    -0.32
    はありません
    -0.31
     startY
    -0.30
     tecnológica
    -0.30
     adaptées
    -0.30
    InjectAttribute
    -0.30
    POSITIVE LOGITS
    \_
    0.79
    _
    0.76
    
    0.65
    MessageOf
    0.64
    Попис
    0.64
    — 
    0.62
    _
    0.62
    @_
    0.60
    '_
    0.60
    ]_
    0.59
    Act Density 0.001%

    No Known Activations