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

    Neuronpedia

    INDEX
    Explanations

    form

    np_max-act · gemini-2.0-flash

    The neuron detects occurrences of mathematical “differential forms” terminology (e.g. words like “differential,” “forms,” “Ω^•,” and related integration notation).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ThreadPool
    -0.06
     valign
    -0.06
    훈
    -0.06
    REL
    -0.06
     ThreadPool
    -0.06
     полі
    -0.06
    icks
    -0.06
    _Right
    -0.06
    άσ
    -0.06
    realm
    -0.06
    POSITIVE LOGITS
    ήμερα
    0.07
    182
    0.07
     Changed
    0.07
     let
    0.06
    硬
    0.06
     الاع
    0.06
     cfg
    0.06
     richTextBox
    0.06
    ﾟ
    0.06
     BigNumber
    0.06
    Act Density 0.006%

    No Known Activations