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

    Neuronpedia

    INDEX
    Explanations

    code problems

    np_max-act · gemini-2.0-flash

    The neuron is essentially “dead” – it never fires (i.e. it doesn’t detect any pattern).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     communic
    -0.07
     مخروط
    -0.07
    (Network
    -0.06
    _inside
    -0.06
    ocused
    -0.06
     Educational
    -0.06
     scrutiny
    -0.06
    structors
    -0.06
    Clinical
    -0.06
     ammunition
    -0.06
    POSITIVE LOGITS
    Voice
    0.07
    qual
    0.07
    ?<
    0.06
     ley
    0.06
    .Android
    0.06
     нас
    0.06
    ipzig
    0.06
     İ
    0.06
     re
    0.06
    олов
    0.06
    Act Density 0.025%

    No Known Activations