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

    Neuronpedia

    INDEX
    Explanations

    technical articles

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric CSS property values and related measurement tokens (e.g. numbers, units like px or %, and terms like margin or negative) in style declarations.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    eddar
    -0.07
    upy
    -0.07
     надання
    -0.06
     Lem
    -0.06
     hubby
    -0.06
    .SceneManagement
    -0.06
     acre
    -0.06
    Popular
    -0.06
     datingsider
    -0.06
     geliş
    -0.06
    POSITIVE LOGITS
     harsh
    0.07
    reset
    0.07
    τερο
    0.07
    /stream
    0.07
    าม
    0.07
     Resize
    0.07
     іншого
    0.06
    (Runtime
    0.06
    ́
    0.06
    	call
    0.06
    Act Density 0.315%

    No Known Activations