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

    Neuronpedia

    INDEX
    Explanations

    workout

    np_max-act · gemini-2.0-flash

    The neuron activates on terms related to physical exercise and workout/training activities.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     feasibility
    -0.07
    	esc
    -0.07
     Happiness
    -0.07
    .pipe
    -0.07
    pipe
    -0.06
     tubes
    -0.06
     branches
    -0.06
     Diss
    -0.06
    人才
    -0.06
     Bus
    -0.06
    POSITIVE LOGITS
     workout
    0.11
     Workout
    0.10
     workouts
    0.09
    aysia
    0.06
    Gun
    0.06
    (dAtA
    0.06
     Orta
    0.06
     tough
    0.06
    Wow
    0.06
    ocr
    0.06
    Act Density 0.005%

    No Known Activations