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

    Neuronpedia

    INDEX
    Explanations

    Technical texts

    np_max-act · gemini-2.0-flash

    The neuron detects occurrences of the word “via,” especially when marking a method or mechanism.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     cerca
    -0.07
    }${
    -0.07
     region
    -0.07
     ninete
    -0.06
     hosp
    -0.06
     ratified
    -0.06
     shelf
    -0.06
    าว
    -0.06
    PAL
    -0.06
     empez
    -0.06
    POSITIVE LOGITS
     مقاله
    0.07
     isNew
    0.07
    arnation
    0.07
    roomId
    0.06
     """",↵
    0.06
     七
    0.06
    orderId
    0.06
     Repo
    0.06
    (CType
    0.06
    _ZONE
    0.06
    Act Density 0.198%

    No Known Activations