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

    Neuronpedia

    INDEX
    Explanations

    {

    np_max-act · gemini-2.0-flash

    This neuron spotlights LaTeX mathematical tokens and commands (e.g. mathcal, mathbb, \mu, \Omega) within the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     sleeper
    -0.07
    arrow
    -0.07
    (weights
    -0.07
    (Z
    -0.07
     Hick
    -0.07
     Gratuit
    -0.07
     Merkez
    -0.06
     máte
    -0.06
    Larry
    -0.06
     γρα
    -0.06
    POSITIVE LOGITS
     आस
    0.06
    कन
    0.06
     capital
    0.06
     errorMsg
    0.06
    zc
    0.06
     homem
    0.06
     ngôi
    0.06
    術
    0.06
     Frequently
    0.06
    Nach
    0.06
    Act Density 0.002%

    No Known Activations