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

    Neuronpedia

    INDEX
    Explanations

    HTML code

    np_max-act · gemini-2.0-flash

    This neuron fires on HTML markup tokens (angle-bracket tags and attribute names).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    olley
    -0.07
     coloured
    -0.06
     remembered
    -0.06
    _background
    -0.06
    段
    -0.06
    fish
    -0.06
    унд
    -0.06
     Base
    -0.06
     loved
    -0.06
     nodes
    -0.06
    POSITIVE LOGITS
     společnosti
    0.07
    0.07
    ;margin
    0.06
     حجم
    0.06
    arsimp
    0.06
     Came
    0.06
     Pero
    0.06
    addresses
    0.06
    通知
    0.06
    -container
    0.06
    Act Density 0.021%

    No Known Activations