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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric tokens (digits and numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    的时候
    -0.07
     augmentation
    -0.06
     died
    -0.06
    HAV
    -0.06
    _coverage
    -0.06
     kurum
    -0.06
    720
    -0.06
     utilizing
    -0.06
    Val
    -0.06
    ,O
    -0.06
    POSITIVE LOGITS
    оит
    0.07
    人民
    0.07
     Luke
    0.07
     einzel
    0.06
     Spider
    0.06
    	resp
    0.06
    .Collections
    0.06
     Carnival
    0.06
    如此
    0.06
    Smarty
    0.06
    Act Density 0.020%

    No Known Activations