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

    Neuronpedia

    INDEX
    Explanations

    o

    np_max-act · gemini-2.0-flash

    This neuron fires on parts of the text that are inside LaTeX‐style math notation (e.g. backslash commands and dollar‐delimited formulas).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     avoid
    -0.07
     bey
    -0.06
     recur
    -0.06
    ='')↵
    -0.06
    �
    -0.06
     gettext
    -0.06
     ци
    -0.06
     flee
    -0.06
     UICollectionView
    -0.06
    >Contact
    -0.06
    POSITIVE LOGITS
    otte
    0.06
     Tales
    0.06
    чества
    0.06
    743
    0.06
    yntax
    0.06
     adultos
    0.06
     ABC
    0.06
    RGB
    0.06
    환
    0.06
    getInt
    0.06
    Act Density 0.002%

    No Known Activations