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

    Neuronpedia

    INDEX
    Explanations

    text/math notation

    np_max-act · gemini-2.0-flash

    This neuron is detecting LaTeX typesetting commands (e.g. the “\text” macro).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ;)
    -0.07
    arp
    -0.06
    aldo
    -0.06
    _adc
    -0.06
     taxis
    -0.06
     شخصی
    -0.06
    ."\
    -0.06
    LINE
    -0.06
     поба
    -0.06
     runaway
    -0.06
    POSITIVE LOGITS
     terre
    0.07
     chang
    0.07
     change
    0.06
    -change
    0.06
     التعليم
    0.06
    입
    0.06
    ़न
    0.06
    нуть
    0.06
    -reader
    0.06
    صر
    0.06
    Act Density 0.015%

    No Known Activations