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

    Neuronpedia

    INDEX
    Explanations

    website code

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric CSS values (especially fractional/decimal measurements) in style rules.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    إن
    -0.08
     Snapshot
    -0.07
     Leak
    -0.07
     Compression
    -0.06
    _HEL
    -0.06
     Specifications
    -0.06
    replacement
    -0.06
    “But
    -0.06
     ids
    -0.06
    Redux
    -0.06
    POSITIVE LOGITS
    (Label
    0.06
    arn
    0.06
     bachelor
    0.06
     Written
    0.06
    (world
    0.06
     COL
    0.06
    _graphics
    0.06
    ��
    0.06
    izzy
    0.06
    áce
    0.06
    Act Density 0.016%

    No Known Activations