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

    Neuronpedia

    INDEX
    Explanations

    Condescending/arrogance

    np_max-act · gemini-2.0-flash

    The neuron fires on words that convey arrogant or condescending attitudes.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _learning
    -0.07
     fats
    -0.07
    ям
    -0.07
    BoundingBox
    -0.06
    (ids
    -0.06
     Garden
    -0.06
    .isBlank
    -0.06
    _proba
    -0.06
    射
    -0.06
    INES
    -0.06
    POSITIVE LOGITS
     premiums
    0.07
    ."
    0.06
    lover
    0.06
         
    0.06
     Comcast
    0.06
     oversh
    0.06
    oning
    0.06
     cái
    0.06
    parcel
    0.06
     zoning
    0.06
    Act Density 0.013%

    No Known Activations