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

    Neuronpedia

    INDEX
    Explanations

    sentence beginnings

    np_max-act · gemini-2.0-flash

    This neuron detects references to embedded infographics or call-outs to view infographics (e.g. tokens like “infographic,” “below,” “details,” “out”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Kin
    -0.07
    예
    -0.07
     Cmd
    -0.07
    /fl
    -0.06
    itable
    -0.06
    /be
    -0.06
    orent
    -0.06
    454
    -0.06
    izable
    -0.06
    -news
    -0.06
    POSITIVE LOGITS
     Julien
    0.07
     Majority
    0.06
    .split
    0.06
    .subplot
    0.06
     spur
    0.06
    )`
    0.06
    .layoutControlItem
    0.06
    ="#">↵
    0.06
     مك
    0.06
    ="#"
    0.06
    Act Density 0.039%

    No Known Activations