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

    Neuronpedia

    INDEX
    Explanations

    mathematical formulas and code

    np_max-act · gemini-2.0-flash

    The neuron is detecting standalone numeric tokens (e.g. digits like “2”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     integers
    -0.07
    ifs
    -0.07
    iendo
    -0.07
     telegram
    -0.06
    <Address
    -0.06
    abb
    -0.06
    butt
    -0.06
     Rai
    -0.06
    ellar
    -0.06
    	ax
    -0.06
    POSITIVE LOGITS
     |-
    0.07
     privacy
    0.06
     leases
    0.06
     Gent
    0.06
    наче
    0.06
    详
    0.06
     $("#
    0.06
    主要
    0.06
    atorium
    0.06
     يتم
    0.06
    Act Density 0.102%

    No Known Activations