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

    Neuronpedia

    INDEX
    Explanations

    Politics and government

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric tokens—especially digits and decimal numbers—highlighting places where figures or data values appear.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     मद
    -0.06
     Ebola
    -0.06
    midi
    -0.06
    -but
    -0.06
     racist
    -0.06
     пользователя
    -0.06
     collaborating
    -0.06
     dreams
    -0.06
     questioning
    -0.06
    Baby
    -0.06
    POSITIVE LOGITS
     Percy
    0.07
    ости
    0.07
    Jul
    0.06
     oblig
    0.06
    eties
    0.06
    itere
    0.06
    ibName
    0.06
     か
    0.06
     
↵
↵
    0.06
    .Utilities
    0.06
    Act Density 0.074%

    No Known Activations