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

    Neuronpedia

    INDEX
    Explanations

    img

    np_max-act · gemini-2.0-flash

    The neuron fires on HTML image tags—i.e. occurrences of `<img>` and its src attribute.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Keith
    -0.08
    Keith
    -0.07
    �
    -0.07
     union
    -0.07
    Marshal
    -0.07
     zá
    -0.07
     SON
    -0.07
    \System
    -0.07
     Tổ
    -0.07
     resourceName
    -0.07
    POSITIVE LOGITS
    img
    0.08
    	bg
    0.07
    instagram
    0.07
    Img
    0.06
    <img
    0.06
    _dims
    0.06
    	img
    0.06
     humor
    0.06
    βολή
    0.06
     img
    0.06
    Act Density 0.003%

    No Known Activations