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

    Neuronpedia

    INDEX
    Explanations

    one

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric literals, especially floating‐point number tokens (decimal values).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Hiệp
    -0.07
     isc
    -0.06
     نيز
    -0.06
    �
    -0.06
     tvor
    -0.06
     capable
    -0.06
    olik
    -0.06
    jom
    -0.06
     Huss
    -0.06
     Λα
    -0.06
    POSITIVE LOGITS
    lásil
    0.06
    �인
    0.06
     illum
    0.06
    LIC
    0.06
    Stopping
    0.06
    			 ↵
    0.06
    DMIN
    0.06
    entries
    0.06
     недостат
    0.06
     CHAPTER
    0.06
    Act Density 0.978%

    No Known Activations