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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions

    np_max-act · gemini-2.0-flash

    The neuron activates on tokens that are purely numeric (integers, fractions, or decimal numbers) in these math‐evaluation lines.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    械
    -0.07
    یان
    -0.06
     menus
    -0.06
     Frankie
    -0.06
     успеш
    -0.06
    表示
    -0.06
    ddy
    -0.06
    ighton
    -0.06
    .getField
    -0.06
    DAO
    -0.06
    POSITIVE LOGITS
     cancelButtonTitle
    0.07
    _Action
    0.07
    nodeValue
    0.06
    "]/
    0.06
    olia
    0.06
    .edge
    0.06
    )./
    0.06
    angstrom
    0.06
    ,.
    0.06
     handc
    0.06
    Act Density 0.007%

    No Known Activations