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

    Neuronpedia

    INDEX
    Explanations

    repeat times

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric counts, durations, and repetition indicators in exercise instructions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     лег
    -0.07
    	ax
    -0.06
    masters
    -0.06
     shapes
    -0.06
    Cou
    -0.06
    “The
    -0.06
    	animation
    -0.06
     uptime
    -0.06
    iki
    -0.06
    Priority
    -0.06
    POSITIVE LOGITS
     vm
    0.07
    .KEY
    0.07
    .big
    0.06
     Citizens
    0.06
     晴
    0.06
     ž
    0.06
     duyệt
    0.06
    ubern
    0.06
     ***↵
    0.06
     β
    0.06
    Act Density 0.005%

    No Known Activations