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

    Neuronpedia

    INDEX
    Explanations

    mathematical equations

    np_max-act · gemini-2.0-flash

    This neuron detects LaTeX math‐mode syntax, i.e. tokens like backslashes, math‐mode commands (e.g. “\,”), and related delimiters (e.g. “^”, “left”, “right”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _feed
    -0.07
    ToJson
    -0.07
     Fault
    -0.07
     flag
    -0.06
    folios
    -0.06
     arou
    -0.06
     Arc
    -0.06
    _div
    -0.06
     reason
    -0.06
     Interrupt
    -0.06
    POSITIVE LOGITS
    커스
    0.07
     kolej
    0.07
     electrónico
    0.07
    et
    0.06
    IGHL
    0.06
    秘
    0.06
     longstanding
    0.06
    .documentElement
    0.06
     федераль
    0.06
     entren
    0.06
    Act Density 0.006%

    No Known Activations