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

    Neuronpedia

    INDEX
    Explanations

    by

    np_max-act · gemini-2.0-flash

    This neuron detects decimal-format number tokens (i.e. floating-point numerals).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     muit
    -0.06
    	Long
    -0.06
     pops
    -0.06
     vede
    -0.06
    _every
    -0.06
     erken
    -0.06
     Greene
    -0.06
    报道
    -0.06
     Ve
    -0.05
     dias
    -0.05
    POSITIVE LOGITS
     culturally
    0.07
     Absolutely
    0.07
    ...");↵
    0.07
    /env
    0.06
    -------------↵
    0.06
     Contrast
    0.06
     μεγ
    0.06
    .openConnection
    0.06
    .createCell
    0.06
     backdrop
    0.06
    Act Density 0.012%

    No Known Activations