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

    Neuronpedia

    INDEX
    Explanations

    leg

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on occurrences of the standalone token “leg.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    SourceType
    -0.07
    320
    -0.07
    County
    -0.07
    Thu
    -0.07
     antioxidant
    -0.07
    696
    -0.07
     shut
    -0.07
     Huang
    -0.06
     Wu
    -0.06
    UUID
    -0.06
    POSITIVE LOGITS
     leg
    0.14
     legs
    0.13
     Leg
    0.10
     Legs
    0.10
     knees
    0.09
     목
    0.08
     Lego
    0.08
     LEGO
    0.08
    Leg
    0.08
     leggings
    0.08
    Act Density 0.011%

    No Known Activations