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

    Neuronpedia

    INDEX
    Explanations

    chromatography

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric measurement tokens (e.g. decimal values, ratios, volumes, concentrations, and units) in methodological descriptions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    encoder
    -0.08
    vak
    -0.07
    <Vec
    -0.07
    ATION
    -0.07
    问题
    -0.07
     SGD
    -0.06
    GAME
    -0.06
    .trip
    -0.06
    WND
    -0.06
    Whole
    -0.06
    POSITIVE LOGITS
    |--
    0.07
     petroleum
    0.07
     Bras
    0.07
     Locations
    0.07
    Balancer
    0.07
    laws
    0.06
    Previously
    0.06
     treadmill
    0.06
    Ability
    0.06
    ئيس
    0.06
    Act Density 0.005%

    No Known Activations