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

    Neuronpedia

    INDEX
    Explanations

    geometry sides

    np_max-act · gemini-2.0-flash

    This neuron never activates—it doesn’t detect any pattern in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _DAYS
    -0.07
    الك
    -0.07
    folder
    -0.07
     mL
    -0.07
    'est
    -0.07
     {};↵
    -0.07
    height
    -0.07
    China
    -0.07
    =',
    -0.06
     listens
    -0.06
    POSITIVE LOGITS
    &&&&
    0.07
     jag
    0.06
     Vog
    0.06
    ّة
    0.06
     episodes
    0.06
     Antoine
    0.06
     Wick
    0.06
     Boise
    0.06
    ningen
    0.06
    	area
    0.06
    Act Density 0.010%

    No Known Activations