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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and symbols

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

    LaTeX math environments

    np_acts-logits-general · gemini-2.0-flash

    Psi begin label

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    CloseOperation
    -0.72
    enumii
    -0.69
    EndContext
    -0.65
    Cyfarwyddwr
    -0.64
    ExtendWith
    -0.61
    Lähteet
    -0.61
    SceneManagement
    -0.60
     ویکی‌پدیای
    -0.60
    BASEPATH
    -0.60
    بوابة
    -0.59
    POSITIVE LOGITS
    \[
    0.30
    >{@
    0.29
    fromnode
    0.29
    richTextPanel
    0.29
    ようになりました
    0.28
    setVerticalGroup
    0.27
    ようになります
    0.27
     ${\
    0.27
    ❚
    0.26
    models
    0.26
    Act Density 0.271%

    No Known Activations