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

    Neuronpedia

    INDEX
    Explanations

    listed

    np_max-act · gemini-2.0-flash

    The neuron consistently lights up on tokens that are floating-point numbers (i.e. numeric strings containing a decimal point).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    35
    -0.07
    	reader
    -0.07
    -back
    -0.06
     ears
    -0.06
     loop
    -0.06
     vaccine
    -0.06
     Dungeons
    -0.06
     Bands
    -0.06
    (o
    -0.06
     Floyd
    -0.06
    POSITIVE LOGITS
     {?}
    0.06
     DAC
    0.06
    .&
    0.06
     forgetting
    0.06
     &(
    0.06
    "',↵
    0.06
     ‘
    0.06
     modelName
    0.06
    _BAND
    0.06
     چگونه
    0.06
    Act Density 0.321%

    No Known Activations