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

    Neuronpedia

    INDEX
    Explanations

    patients

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on numeric expressions and measurements (e.g. counts, durations, percentages) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Launch
    -0.07
     photograph
    -0.07
    sample
    -0.07
     market
    -0.07
     издел
    -0.07
    Device
    -0.07
     boats
    -0.07
     perspective
    -0.07
     economics
    -0.07
     process
    -0.06
    POSITIVE LOGITS
    (sel
    0.06
    _For
    0.06
    gif
    0.06
    aleza
    0.06
    _wind
    0.06
     Erdogan
    0.06
    vrd
    0.06
    nun
    0.06
    .↵↵↵↵↵
    0.06
    λευ
    0.06
    Act Density 0.012%

    No Known Activations