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

    Neuronpedia

    INDEX
    Explanations

    exercise body positions

    np_max-act · gemini-2.0-flash

    exercise-related terms or phrases focused on rehabilitation and recovery.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron fires on special structural or formatting tokens (e.g. metadata tags, section headers, and numbered list markers) rather than on ordinary words.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     planning
    -0.07
    atch
    -0.07
    _ax
    -0.06
    .parameter
    -0.06
    ोस
    -0.06
     flux
    -0.06
     financing
    -0.06
    .logo
    -0.06
     investigators
    -0.06
     laboratories
    -0.06
    POSITIVE LOGITS
     eql
    0.07
    .tcp
    0.07
    $response
    0.06
    ();"
    0.06
    /kernel
    0.06
     země
    0.06
     │
    0.06
     yahoo
    0.06
    Runtime
    0.06
    askell
    0.06
    Act Density 0.010%

    No Known Activations