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

    Neuronpedia

    INDEX
    Explanations

    periods and sentence structures that indicate conclusions or summaries

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

    language and technical identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    …
    -0.46
     Best
    -0.43
     Dodson
    -0.42
    ….
    -0.42
     officially
    -0.40
     …
    -0.40
     Full
    -0.40
    galo
    -0.39
     Hers
    -0.38
    ……
    -0.38
    POSITIVE LOGITS
     كومونز
    0.83
    ValueStyle
    0.73
     estekak
    0.72
     للمعارف
    0.68
    httphttps
    0.67
    HomeAsUpEnabled
    0.65
     lisäksi
    0.65
    sizeCache
    0.65
     typelib
    0.65
    Становништво
    0.60
    Act Density 0.033%

    No Known Activations