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

    Neuronpedia

    INDEX
    Explanations

    Journalists/Authors

    np_max-act · gemini-2.0-flash

    The neuron activates on proper names in bylines and citations—i.e. author or reporter names.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    TECTED
    -0.07
     آزم
    -0.07
     Omaha
    -0.06
    _collision
    -0.06
    []{↵
    -0.06
     pygame
    -0.06
    (td
    -0.06
    pygame
    -0.06
     скор
    -0.06
     &___
    -0.06
    POSITIVE LOGITS
     Clean
    0.08
    lip
    0.07
     Dietary
    0.07
    -display
    0.06
    Loan
    0.06
    ace
    0.06
     RE
    0.06
     standout
    0.06
     locks
    0.06
    貨
    0.06
    Act Density 0.011%

    No Known Activations