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

    Neuronpedia

    INDEX
    Explanations

    Technical descriptions

    np_max-act · gemini-2.0-flash

    This neuron detects numeric measurements paired with units (e.g., dimensions, weights, heights) in product descriptions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ertino
    -0.07
     locator
    -0.06
     northwest
    -0.06
    (instance
    -0.06
    PLAYER
    -0.06
     took
    -0.06
     possess
    -0.06
    icester
    -0.06
    aklı
    -0.06
    Played
    -0.06
    POSITIVE LOGITS
     laat
    0.07
     figur
    0.07
     بازبینی
    0.07
    สว
    0.07
    }`
    0.06
    .isnan
    0.06
     أع
    0.06
     Наг
    0.06
     Banc
    0.06
    ؟
    0.06
    Act Density 0.084%

    No Known Activations