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

    Neuronpedia

    INDEX
    Explanations

    news events

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on numerical tokens—especially floating-point or decimal numbers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     FIXME
    -0.07
     paramInt
    -0.07
    。",↵
    -0.06
    мерикан
    -0.06
    ZX
    -0.06
     womens
    -0.06
    webtoken
    -0.06
    XF
    -0.06
     возрасте
    -0.06
    Pause
    -0.06
    POSITIVE LOGITS
    DATABASE
    0.08
     Accent
    0.06
    428
    0.06
    /mysql
    0.06
     armored
    0.06
     Roma
    0.06
    alah
    0.06
     Maul
    0.06
     diagon
    0.06
     hemp
    0.06
    Act Density 0.329%

    No Known Activations