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

    Neuronpedia

    INDEX
    Explanations

    Opening brackets

    np_max-act · gemini-2.0-flash

    This neuron detects LaTeX‐style mathematical expressions, especially tokens inside math formulas (e.g. backslash commands, braces, and symbol sequences).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     papers
    -0.06
     bile
    -0.06
     Lovely
    -0.06
    Ocean
    -0.06
     intens
    -0.06
    ậu
    -0.06
    Mind
    -0.06
     sahip
    -0.06
     independent
    -0.05
    黎
    -0.05
    POSITIVE LOGITS
    ？”
    0.07
    _fecha
    0.07
    ？」
    0.07
    addGroup
    0.07
    Ubuntu
    0.07
    _Panel
    0.07
    för
    0.06
    (--
    0.06
    BackColor
    0.06
     gezocht
    0.06
    Act Density 0.007%

    No Known Activations