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

    Neuronpedia

    INDEX
    Explanations

    punctuation, specifically comma usage

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

    Followed by discourse markers/adverbs

    np_acts-logits-general · gemini-2.0-flash

    contrast and elaboration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MigrationBuilder
    -0.74
     فريبيس
    -0.71
     resourceCulture
    -0.62
    webElementXpaths
    -0.59
    permitAll
    -0.59
     nemlig
    -0.58
     TMPro
    -0.58
    which
    -0.57
    initWith
    -0.56
    podar
    -0.55
    POSITIVE LOGITS
     parado
    0.78
     importantly
    0.78
     ironically
    0.72
     interestingly
    0.71
    contr
    0.71
     contrary
    0.69
     unlike
    0.69
     conversely
    0.67
     oddly
    0.66
     needless
    0.65
    Act Density 0.209%

    No Known Activations