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

    Neuronpedia

    INDEX
    Explanations

    buildings

    np_max-act · gemini-2.0-flash

    The neuron activates on words naming the type or function of a building (e.g. “bank,” “school,” “library”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     LinearGradient
    -0.06
     weary
    -0.06
    _dy
    -0.06
     doe
    -0.06
    (^
    -0.06
     ;)
    -0.06
    Shape
    -0.06
     Doe
    -0.06
    .enums
    -0.06
    दर
    -0.05
    POSITIVE LOGITS
    .assertIsNot
    0.07
    سبة
    0.07
    ','.
    0.07
     فريق
    0.07
     Bathroom
    0.07
    場
    0.07
     방문
    0.06
     nombres
    0.06
    徳
    0.06
    $(".
    0.06
    Act Density 0.042%

    No Known Activations