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

    Neuronpedia

    INDEX
    Explanations

    sign

    np_max-act · gemini-2.0-flash

    The neuron fires on instances of the word “sign,” marking where a measurement’s sign or polarity is being specified.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _Buffer
    -0.07
    yah
    -0.06
     درجه
    -0.06
    Cop
    -0.06
    Events
    -0.06
     پروژه
    -0.06
    projects
    -0.06
     derece
    -0.06
    /u
    -0.06
    .entry
    -0.06
    POSITIVE LOGITS
    toolbox
    0.07
     použití
    0.07
    .setTo
    0.07
    arResult
    0.07
    )","
    0.06
    nonnull
    0.06
     DataType
    0.06
     رح
    0.06
     unfore
    0.06
     orientations
    0.06
    Act Density 0.033%

    No Known Activations