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 TeX/LaTeX math notation (tokens like “\”, “{”, “}”, “^”, “_”, “\frac”, and related formula delimiters).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     litigation
    -0.07
    aka
    -0.07
     scrollTop
    -0.07
    อนด
    -0.06
     chor
    -0.06
    wcs
    -0.06
     Respons
    -0.06
    _mobile
    -0.06
    frames
    -0.06
     bind
    -0.06
    POSITIVE LOGITS
    .layers
    0.06
     Isl
    0.06
    .getLabel
    0.06
    �
    0.06
    ensely
    0.06
    .Reg
    0.06
     amounted
    0.06
    aments
    0.06
     skirts
    0.06
     jew
    0.06
    Act Density 0.010%

    No Known Activations