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

    Neuronpedia

    INDEX
    Explanations

    mathematical notation

    np_max-act · gemini-2.0-flash

    This neuron detects LaTeX‐style mathematical expressions and symbols, especially those related to C*-algebra definitions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    長
    -0.07
    由于
    -0.07
     haha
    -0.06
     :]↵
    -0.06
     nă
    -0.06
    <R
    -0.06
     أب
    -0.06
     роз
    -0.06
     наступ
    -0.06
    处理
    -0.06
    POSITIVE LOGITS
    andatory
    0.07
    õi
    0.07
    useppe
    0.06
    Unknown
    0.06
    _EM
    0.06
     Lumpur
    0.06
     지방
    0.06
     Unknown
    0.06
     sigmoid
    0.06
    IMUM
    0.06
    Act Density 0.022%

    No Known Activations