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

    Neuronpedia

    INDEX
    Explanations

    ="

    np_max-act · gemini-2.0-flash

    The neuron lights up on the actual URL/path strings in HTML link (href) attributes.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    madan
    -0.07
    blue
    -0.07
     conscious
    -0.07
     subjected
    -0.06
    loggedin
    -0.06
     пло
    -0.06
     bout
    -0.06
    民主
    -0.06
    �다
    -0.06
    شهر
    -0.06
    POSITIVE LOGITS
    	Log
    0.07
    Ž
    0.07
    All
    0.07
     utiliz
    0.07
     والح
    0.07
     converge
    0.06
    ements
    0.06
    .showMessageDialog
    0.06
    <W
    0.06
     отсутств
    0.06
    Act Density 0.012%

    No Known Activations