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

    Neuronpedia

    INDEX
    Explanations

    math formatting

    np_max-act · gemini-2.0-flash

    This neuron activates on LaTeX/math‐mode formatting tokens (e.g., backslashes, braces, subscript markers, and numeric/math symbols).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     نفر
    -0.06
    .textField
    -0.06
     عدم
    -0.06
    -even
    -0.06
     getMenuInflater
    -0.06
    ني
    -0.06
    .Infrastructure
    -0.06
    awei
    -0.06
     NTN
    -0.06
     SYSTEM
    -0.06
    POSITIVE LOGITS
    emen
    0.07
    ordo
    0.07
     lottery
    0.07
     relative
    0.07
    uggest
    0.07
     according
    0.06
    running
    0.06
     člověk
    0.06
    iyet
    0.06
     selectedIndex
    0.06
    Act Density 0.002%

    No Known Activations