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

    Neuronpedia

    INDEX
    Explanations

    interjections and conjunctions used in conversational contexts

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

    introducing a reason or alternative

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    BufferException
    -0.46
    脚注の使い方
    -0.46
    findung
    -0.40
    Ầ
    -0.39
    وه
    -0.39
    jaardag
    -0.39
    Jîn
    -0.38
    ầu
    -0.38
    ствием
    -0.38
     margins
    -0.38
    POSITIVE LOGITS
    IUrlHelper
    0.50
     beginnetje
    0.42
     actionPerformed
    0.40
    InvalidProtocol
    0.40
    tagHelperRunner
    0.40
    GoogleApiClient
    0.38
    rscheinlichkeit
    0.38
    getManager
    0.38
    游戏特色
    0.37
     sumpay
    0.36
    Act Density 0.234%

    No Known Activations