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

    Neuronpedia

    INDEX
    Explanations

    A

    np_max-act · gemini-2.0-flash

    This neuron fires on occurrences of the matrix variable “A” (especially in contexts like “Matrix A ist …”)—i.e. when the text is referring to the matrix A.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     bajo
    -0.07
    .ManyToMany
    -0.06
    amentos
    -0.06
    (players
    -0.06
    ),
↵
    -0.06
    cmc
    -0.06
    imating
    -0.06
    onde
    -0.06
    ён
    -0.06
    [attr
    -0.06
    POSITIVE LOGITS
     (?
    0.07
     [+
    0.07
    ATOM
    0.07
    効
    0.06
    iov
    0.06
     "?
    0.06
    γωγή
    0.06
    iola
    0.06
     profitability
    0.06
     ranked
    0.06
    Act Density 0.037%

    No Known Activations