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

    Neuronpedia

    INDEX
    Explanations

    phrases that provide strong advice or recommendations

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

    recommendations and advice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Pingback
    -0.58
    انجليز
    -0.51
     ModelExpression
    -0.51
    contentPane
    -0.50
    ftan
    -0.50
     useAppContext
    -0.49
     myſelf
    -0.48
     ujednoznacz
    -0.47
    ValueStyle
    -0.47
     AssemblyCulture
    -0.47
    POSITIVE LOGITS
     recommended
    0.84
     recommend
    0.81
     advised
    0.80
     recomienda
    0.79
    建议
    0.73
     recommends
    0.73
    建議
    0.72
     recommendation
    0.72
    recommended
    0.71
     recomand
    0.71
    Act Density 0.111%

    No Known Activations