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

    Neuronpedia

    INDEX
    Explanations

    gymnastics

    np_max-act · gemini-2.0-flash

    This neuron activates on occurrences of the word “gymnastics” (including its parts like “gymn,” “astic,” or “astics”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    럼
    -0.07
    eload
    -0.06
    )
↵
↵
    -0.06
    ,args
    -0.06
    _names
    -0.06
     gut
    -0.06
    .RE
    -0.06
     Brady
    -0.06
    _datasets
    -0.06
    _RELEASE
    -0.06
    POSITIVE LOGITS
     gymn
    0.09
     Người
    0.07
    getLast
    0.06
     Vous
    0.06
    ọi
    0.06
     Birthday
    0.06
    ussen
    0.06
     Denmark
    0.06
     Gym
    0.06
     gamb
    0.06
    Act Density 0.003%

    No Known Activations