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

    Neuronpedia

    INDEX
    Explanations

    [@

    np_max-act · gemini-2.0-flash

    This neuron detects numeric tokens with decimal fractions (e.g. “0.53955…”, “2.08984…”) typically found inside reference or citation markers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Buildings
    -0.07
    liquid
    -0.07
    fluid
    -0.07
    ز
    -0.07
     ethnic
    -0.06
    TD
    -0.06
    -0.06
     REVIEW
    -0.06
    lerdir
    -0.06
    tweets
    -0.06
    POSITIVE LOGITS
    rawl
    0.07
    (chart
    0.06
     spep
    0.06
    	puts
    0.06
     cue
    0.06
     grues
    0.06
    )#
    0.06
     educating
    0.06
     견
    0.06
     نصب
    0.06
    Act Density 0.012%

    No Known Activations