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

    Neuronpedia

    INDEX
    Explanations

    body parts

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric tokens used to enumerate steps or specify counts, sets, reps, or durations in workout instructions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    embrance
    -0.07
    ْع
    -0.07
    Gro
    -0.06
    ering
    -0.06
    άνα
    -0.06
    	D
    -0.06
    Law
    -0.06
    classes
    -0.06
     Presenter
    -0.06
     neurons
    -0.06
    POSITIVE LOGITS
    /ayushman
    0.07
     спроб
    0.07
    fadeOut
    0.07
    ::__
    0.07
     srov
    0.06
    (resolve
    0.06
    _ABI
    0.06
     harek
    0.06
    shortcut
    0.06
    portlet
    0.06
    Act Density 0.006%

    No Known Activations