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

    Neuronpedia

    INDEX
    Explanations

    Math

    np_max-act · gemini-2.0-flash

    This neuron is detecting the presence of numeric digits and arithmetic operators (e.g. “1” and “+”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .Initialize
    -0.06
    056
    -0.06
     tín
    -0.06
     autoc
    -0.06
     rap
    -0.06
    _req
    -0.06
    Town
    -0.06
     MemoryStream
    -0.06
     LU
    -0.06
    金融
    -0.06
    POSITIVE LOGITS
    …”↵↵
    0.07
    인이
    0.07
    CreatedBy
    0.07
    увався
    0.07
     emails
    0.06
     تحت
    0.06
    ождение
    0.06
    .`);↵
    0.06
    Ionic
    0.06
    plash
    0.06
    Act Density 0.020%

    No Known Activations