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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and formatting in equations

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

    "$$" and "where" in equations

    np_acts-logits-general · gemini-2.0-flash

    introducing definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    曖昧さ回避
    -0.70
    Хьажоргаш
    -0.69
    __(/*!
    -0.68
    脚注の使い方
    -0.67
    ThroughAttribute
    -0.60
     MutableLiveData
    -0.60
    dymyr
    -0.60
     تضيفلها
    -0.59
    NewUrlParser
    -0.59
    ValueStyle
    -0.59
    POSITIVE LOGITS
    where
    0.64
    Here
    0.59
    ↵
    0.59
    with
    0.57
    and
    0.57
    which
    0.57
    for
    0.57
     Here
    0.55
    here
    0.54
    例文帳に追加
    0.52
    Act Density 0.333%

    No Known Activations