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

    Neuronpedia

    INDEX
    Explanations

    well

    np_max-act · gemini-2.0-flash

    The neuron activates on floating‐point numeric tokens—that is, numbers containing a decimal point.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ра
    -0.07
     rotten
    -0.07
    δια
    -0.07
     hookers
    -0.06
     garment
    -0.06
     quadrant
    -0.06
     swamp
    -0.06
     Серед
    -0.06
     Борис
    -0.06
     underestimate
    -0.06
    POSITIVE LOGITS
     QApplication
    0.07
    Concurrency
    0.07
     CommonModule
    0.07
    ij
    0.07
     HomeController
    0.06
     undef
    0.06
     Johann
    0.06
    771
    0.06
     skilled
    0.06
    .STATE
    0.06
    Act Density 0.005%

    No Known Activations