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

    Neuronpedia

    INDEX
    Explanations

    terms related to incremental changes, particularly in the context of growth or improvement

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

    Comparative adjectives/adverbs

    np_acts-logits-general · gemini-2.0-flash

    frequency words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ThroughAttribute
    -0.71
    tangentMode
    -0.64
     /\.(
    -0.58
     /\.
    -0.57
    bootstrapcdn
    -0.54
     investissements
    -0.53
    exitRule
    -0.53
    contentLoaded
    -0.53
     مشارکت‌کنندگان
    -0.52
    setupUi
    -0.52
    POSITIVE LOGITS
     daily
    2.42
     every
    2.17
     annually
    2.08
     everyday
    2.05
    daily
    2.02
     weekly
    2.01
     everytime
    1.94
    every
    1.86
     yearly
    1.86
     constantly
    1.84
    Act Density 0.896%

    No Known Activations