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

    Neuronpedia

    INDEX
    Explanations

    YUV video encoding

    np_max-act · gemini-2.0-flash

    The neuron fires on mentions of color‐space component labels (e.g. Y, UV, RGB).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     pavement
    -0.07
    /signup
    -0.07
    .rectangle
    -0.07
    DataSet
    -0.06
     době
    -0.06
    sorting
    -0.06
    richText
    -0.06
    !!}</
    -0.06
     Isaiah
    -0.06
    attack
    -0.06
    POSITIVE LOGITS
    noc
    0.07
     realidad
    0.07
     Chí
    0.06
     servic
    0.06
     Scholar
    0.06
     Sherman
    0.06
    -bearing
    0.06
    _symbol
    0.06
     Soda
    0.06
     Harvard
    0.06
    Act Density 0.004%

    No Known Activations