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

    Neuronpedia

    INDEX
    Explanations

    just/simply

    np_max-act · gemini-2.0-flash

    This neuron responds to floating-point numeric tokens (decimal numbers) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    canvas
    -0.07
    :eq
    -0.06
     wcs
    -0.06
     reach
    -0.06
    arent
    -0.06
    Color
    -0.06
    ForeColor
    -0.06
    clear
    -0.06
    cmp
    -0.06
     Gum
    -0.06
    POSITIVE LOGITS
     indicted
    0.07
    (String
    0.07
    uncia
    0.07
     radiation
    0.06
     sonic
    0.06
    矿
    0.06
    ("~/
    0.06
     madness
    0.06
    	o
    0.06
    РО
    0.06
    Act Density 0.024%

    No Known Activations