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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    mathematical combinations and permutations involving constraints on letters or digits.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron responds to numeric tokens and combinatorial/math notation (digits, binomial coefficients, factorials, and related symbols).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    恨
    -0.07
     thank
    -0.07
     contar
    -0.07
     defeating
    -0.07
    CPF
    -0.07
     admiration
    -0.06
     disproportionately
    -0.06
    _VARIABLE
    -0.06
     bets
    -0.06
    ण
    -0.06
    POSITIVE LOGITS
    dent
    0.07
    -&
    0.06
    ...↵↵↵↵
    0.06
    ิจกรรม
    0.06
    -viol
    0.06
     따른
    0.06
    .geo
    0.06
     elim
    0.06
    ^{-
    0.06
    viewer
    0.06
    Act Density 0.016%

    No Known Activations