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

    Neuronpedia

    INDEX
    Explanations

    Shipping quantities

    np_max-act · gemini-2.0-flash

    The neuron activates on tokens naming containers or bulk storage units (e.g., barrels, kegs, pallets) used to package or transport products.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    τικά
    -0.06
    �
    -0.06
    lags
    -0.06
     пап
    -0.06
    ьте
    -0.06
     monoc
    -0.06
    _marshaled
    -0.06
     jue
    -0.06
    MarshalAs
    -0.06
     Jens
    -0.06
    POSITIVE LOGITS
    reset
    0.07
     holiday
    0.07
     horse
    0.07
    -return
    0.07
     vyt
    0.07
    .RestController
    0.06
    .ID
    0.06
    .uri
    0.06
    Returning
    0.06
    _dd
    0.06
    Act Density 0.022%

    No Known Activations