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

    Neuronpedia

    INDEX
    Explanations

    Japanese patents

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric tokens and number-based references (e.g. section numbers, patent or publication numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ende
    -0.06
    foundation
    -0.06
     澳
    -0.06
    ペ
    -0.06
     denn
    -0.06
     prostředí
    -0.06
    acak
    -0.06
     columnist
    -0.06
    atha
    -0.06
     BOTH
    -0.06
    POSITIVE LOGITS
    _DB
    0.07
    _DEVICES
    0.06
    allocation
    0.06
    收入
    0.06
    GetY
    0.06
    ─
    0.06
    .win
    0.06
    喜欢
    0.06
    	b
    0.06
     формы
    0.06
    Act Density 0.008%

    No Known Activations