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

    Neuronpedia

    INDEX
    Explanations

    Bright colors

    np_max-act · gemini-2.0-flash

    The neuron activates on adjectives and phrases that describe vivid, bright, or bold colors.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Model
    -0.07
    gger
    -0.07
    _date
    -0.07
    ToString
    -0.06
     model
    -0.06
     blur
    -0.06
    db
    -0.06
    hu
    -0.06
    space
    -0.06
    _year
    -0.06
    POSITIVE LOGITS
     التعليم
    0.07
    �
    0.07
     trhu
    0.06
     İli
    0.06
     масла
    0.06
     اجتماع
    0.06
    verige
    0.06
     ceasefire
    0.06
     stockholm
    0.06
    constexpr
    0.06
    Act Density 0.018%

    No Known Activations