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

    Neuronpedia

    INDEX
    Explanations

    mathematical notations and formal structures related to models and probabilities

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

    LaTeX equations and expressions

    np_acts-logits-general · gemini-2.0-flash

    mathematical formulas and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     незавершена
    -0.73
    SharedCtor
    -0.68
     snippetHide
    -0.66
    DoubleQuotes
    -0.66
    TypedDataSet
    -0.65
    VersionUID
    -0.65
    CppMethod
    -0.65
    WithIOException
    -0.65
    exitRule
    -0.65
     noDo
    -0.65
    POSITIVE LOGITS
    CJK
    0.66
    http
    0.57
     http
    0.56
    left
    0.53
    <i>
    0.52
    frac
    0.48
    <b>
    0.48
    https
    0.46
    <em>
    0.45
     “
    0.45
    Act Density 0.215%

    No Known Activations