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

    Neuronpedia

    INDEX
    Explanations

    technical writing

    np_max-act · gemini-2.0-flash

    The neuron fires on decimal numeric tokens (numbers with fractional parts) indicating measurements or parameter values.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     pleasant
    -0.07
     ла
    -0.07
     refinement
    -0.07
     руки
    -0.06
     लक
    -0.06
    REQ
    -0.06
     پرد
    -0.06
    _Data
    -0.06
    	input
    -0.06
    .start
    -0.06
    POSITIVE LOGITS
     urging
    0.07
    σε
    0.07
     Між
    0.06
     engaging
    0.06
    .randomUUID
    0.06
     banc
    0.06
     mdb
    0.06
     Virginia
    0.06
    {lng
    0.06
     newsletter
    0.06
    Act Density 0.005%

    No Known Activations