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

    Neuronpedia

    INDEX
    Explanations

    strong recommendations and suggestions in the text

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

    preceding a recommendation or advice

    np_acts-logits-general · gemini-2.0-flash

    suggesting or recommending

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ValueStyle
    -0.51
     ujednoznacz
    -0.50
    depuis
    -0.50
    曖昧さ回避
    -0.48
    SpringBootTest
    -0.46
     verlä
    -0.45
     ModelExpression
    -0.44
    ftan
    -0.44
     juſ
    -0.44
     CreateTagHelper
    -0.43
    POSITIVE LOGITS
     recommended
    0.92
     advised
    0.90
     recommend
    0.84
     recommends
    0.77
    recommended
    0.76
    建议
    0.75
     advise
    0.74
    advised
    0.74
    建議
    0.74
     Recommended
    0.73
    Act Density 0.219%

    No Known Activations