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

    Neuronpedia

    INDEX
    Explanations

    years

    np_max-act · gemini-2.0-flash

    This neuron fires on numeric tokens—especially years and other multi-digit numbers—within the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     всп
    -0.07
     Odin
    -0.07
     rival
    -0.07
     Bruce
    -0.06
     pollution
    -0.06
     University
    -0.06
     Klaus
    -0.06
     musician
    -0.06
    University
    -0.06
    -Д
    -0.06
    POSITIVE LOGITS
    subscriber
    0.07
    _ter
    0.06
     Geological
    0.06
    <object
    0.06
    stored
    0.06
    GLfloat
    0.06
    andReturn
    0.06
    isEmpty
    0.06
     pravděpodob
    0.06
    toThrow
    0.06
    Act Density 0.255%

    No Known Activations