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

    Neuronpedia

    INDEX
    Explanations

    int

    np_max-act · gemini-2.0-flash

    This neuron activates on TeX‐style mathematical tokens (e.g. “\int,” “\frac,” “\sqrt,” numeric formula elements) marking segments written in math notation.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Bailey
    -0.07
    architecture
    -0.07
     MF
    -0.07
     Mavericks
    -0.07
     pods
    -0.07
     Oliveira
    -0.07
     detected
    -0.07
     Movies
    -0.06
     detect
    -0.06
    -game
    -0.06
    POSITIVE LOGITS
    masına
    0.07
    ισμός
    0.07
     इसस
    0.07
    grund
    0.06
    손
    0.06
    ㆍ동
    0.06
     đó
    0.06
    精神
    0.06
    ерах
    0.06
    科技有限公司
    0.06
    Act Density 0.010%

    No Known Activations