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

    Neuronpedia

    INDEX
    Explanations

    references to programming concepts and data structures

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

    <start_of_turn> user

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    transQ
    -0.93
    RenderAtEndOf
    -0.91
    fortawesome
    -0.88
    posedge
    -0.86
     surla
    -0.85
     wireType
    -0.83
    setVerticalGroup
    -0.83
     betweenstory
    -0.83
     numberOfRows
    -0.82
     AssemblyVersion
    -0.81
    POSITIVE LOGITS
     often
    0.40
     b
    0.40
    -
    0.40
     M
    0.37
     could
    0.37
    Kaynakça
    0.37
     S
    0.37
     annonces
    0.36
     '
    0.35
    ?
    0.35
    Act Density 0.009%

    No Known Activations