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

    Neuronpedia

    INDEX
    Explanations

    Article snippets

    np_max-act · gemini-2.0-flash

    The neuron fires selectively on numeric tokens (especially numbers and decimal values).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     microscopic
    -0.07
     angry
    -0.07
     affiliated
    -0.07
    Toggle
    -0.07
    435
    -0.06
    365
    -0.06
    凌
    -0.06
     survival
    -0.06
     Xperia
    -0.06
    775
    -0.06
    POSITIVE LOGITS
     intox
    0.07
    (resp
    0.07
     apply
    0.06
     Studi
    0.06
     并
    0.06
    #![
    0.06
     може
    0.06
     BOOL
    0.06
    lett
    0.06
    _gl
    0.06
    Act Density 0.060%

    No Known Activations