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

    Neuronpedia

    INDEX
    Explanations

    Population statistics

    np_max-act · gemini-2.0-flash

    The neuron is detecting numerical statistic tokens (e.g. population counts, percentages, and decimal figures).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Unters
    -0.07
     algum
    -0.07
     polít
    -0.06
     animator
    -0.06
    agon
    -0.06
     تور
    -0.06
     boils
    -0.06
     jurors
    -0.06
    )을
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     Я
    0.07
    奔
    0.06
     Subscription
    0.06
     pot
    0.06
    /filepath
    0.06
    mour
    0.06
    dic
    0.06
     DataType
    0.06
     Yeah
    0.06
    _rho
    0.06
    Act Density 0.001%

    No Known Activations