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

    Neuronpedia

    INDEX
    Explanations

    Quantities

    np_max-act · gemini-2.0-flash

    The neuron responds to words that express quantities or counts—e.g. numerals and quantifiers like “one,” “multiple,” “more,” “two,” etc.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Athena
    -0.07
     AM
    -0.07
     actualizar
    -0.06
     ط
    -0.06
    -prev
    -0.06
     neat
    -0.06
    elidir
    -0.06
     RD
    -0.06
     }}"
    -0.06
     completa
    -0.06
    POSITIVE LOGITS
    .commons
    0.06
     LCS
    0.06
     reconstructed
    0.06
     питань
    0.06
     servic
    0.06
    ManagedObjectContext
    0.06
     pulmonary
    0.06
    .UseText
    0.06
    .springframework
    0.06
     принцип
    0.06
    Act Density 0.028%

    No Known Activations