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

    Neuronpedia

    INDEX
    Explanations

    news snippets

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on words at the beginnings of sentences (i.e. the first token following a sentence boundary).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     "/"
    -0.07
    contracts
    -0.07
     mụn
    -0.06
    PostalCodes
    -0.06
    policy
    -0.06
     sunscreen
    -0.06
    Det
    -0.06
     pleaded
    -0.06
    Calc
    -0.06
    iii
    -0.06
    POSITIVE LOGITS
    -of
    0.07
     QGraphics
    0.06
    弥
    0.06
    是一个
    0.06
    incre
    0.06
     employee
    0.06
     By
    0.06
    (Qt
    0.06
     UIG
    0.06
    asterxml
    0.06
    Act Density 0.028%

    No Known Activations