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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to engineering and project management

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

    preceding adverbs/qualifiers

    np_acts-logits-general · gemini-2.0-flash

    dog training collars and obedience

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    脚注の使い方
    -1.06
     للمعارف
    -0.93
     propOrder
    -0.89
     ویکی‌پدیا
    -0.86
     <=",
    -0.82
    WithIOException
    -0.82
     مرئيه
    -0.79
    tagHelperRunner
    -0.78
    DockStyle
    -0.78
     فريبيس
    -0.76
    POSITIVE LOGITS
     additionally
    0.88
     ought
    0.80
     utilized
    0.79
     nonetheless
    0.78
     nevertheless
    0.78
     utilizing
    0.74
     asimismo
    0.74
     neighborhood
    0.72
     observe
    0.69
     likewise
    0.69
    Act Density 0.794%

    No Known Activations