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

    Neuronpedia

    INDEX
    Explanations

    mathematical functions/equations

    np_max-act · gemini-2.0-flash

    This neuron detects occurrences of floating‐point numeric literals (numbers containing a decimal point).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Monitoring
    -0.07
    停
    -0.06
    528
    -0.06
     '{
    -0.06
     appealed
    -0.06
     Emperor
    -0.06
    endar
    -0.06
    ultan
    -0.06
    -centric
    -0.06
    -[
    -0.06
    POSITIVE LOGITS
     QPoint
    0.07
     무
    0.07
    |unique
    0.07
    	core
    0.06
     csvfile
    0.06
     опред
    0.06
     LSM
    0.06
    (QtCore
    0.06
    訳
    0.06
     cbo
    0.06
    Act Density 0.014%

    No Known Activations