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

    Neuronpedia

    INDEX
    Explanations

    other

    np_max-act · gemini-2.0-flash

    The neuron chiefly responds to occurrences of the word “other.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    От
    -0.06
    igrams
    -0.06
     oversized
    -0.06
    .assertNotNull
    -0.06
     dazu
    -0.06
     Quebec
    -0.06
    survey
    -0.06
     Pass
    -0.06
    HasBeenSet
    -0.06
     witty
    -0.05
    POSITIVE LOGITS
    енты
    0.08
    isse
    0.07
     bal
    0.07
     판
    0.07
    _document
    0.06
    execution
    0.06
    ))
↵
    0.06
     gemeins
    0.06
     endPoint
    0.06
     Execution
    0.06
    Act Density 0.032%

    No Known Activations