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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash

    This neuron activates on CSS style declarations—tokens defining style rules (e.g. “.style…”, “font‐size:”, “color:”, pixel values, etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Dome
    -0.08
    861
    -0.07
     NF
    -0.07
     flo
    -0.07
     Esk
    -0.07
    Ke
    -0.07
     SME
    -0.06
     wholes
    -0.06
     Angle
    -0.06
     benzer
    -0.06
    POSITIVE LOGITS
     conviction
    0.06
    ��索
    0.06
     shuffled
    0.06
     QImage
    0.06
    queryString
    0.06
     impressed
    0.06
    และ
    0.06
    럽
    0.06
     يع
    0.06
    -command
    0.06
    Act Density 0.016%

    No Known Activations