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

    Neuronpedia

    INDEX
    Explanations

    cycling

    np_max-act · gemini-2.0-flash

    The neuron selectively responds to terms naming physical exercises or workout activities (e.g. cycling, rowing, jumping, rows).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    bags
    -0.07
    _documents
    -0.07
     iod
    -0.07
    .Score
    -0.07
    gars
    -0.07
    .).
    -0.07
     setData
    -0.07
    ázky
    -0.06
    $/
    -0.06
    _VECTOR
    -0.06
    POSITIVE LOGITS
     централь
    0.07
     attempt
    0.06
    œ
    0.06
    _while
    0.06
     plain
    0.06
     CIM
    0.06
    imbledon
    0.06
     Avengers
    0.06
     attempting
    0.06
     Junction
    0.06
    Act Density 0.004%

    No Known Activations