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

    Neuronpedia

    INDEX
    Explanations

    instances of emphasis or significant data points within discussions

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

    above

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    writeFieldEnd
    -0.70
    RenderAtEndOf
    -0.69
    principalColumn
    -0.65
    addContainerGap
    -0.62
    ailleurs
    -0.59
     &___
    -0.58
     AssemblyCulture
    -0.58
    ckså
    -0.56
    exitRule
    -0.56
    +#+
    -0.56
    POSITIVE LOGITS
    Above
    0.76
    above
    0.67
     above
    0.67
     Above
    0.66
     this
    0.65
    Based
    0.59
     acima
    0.55
     Based
    0.54
    上記
    0.54
    This
    0.51
    Act Density 0.185%

    No Known Activations