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

    Neuronpedia

    INDEX
    Explanations

    presence or absence of data

    np_max-act · gemini-2.0-flash

    This neuron activates on floating-point numeric literals (i.e. tokens representing decimal numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     chased
    -0.06
     chaining
    -0.06
     cutter
    -0.06
    >K
    -0.06
     convin
    -0.06
    .routing
    -0.06
    ISTR
    -0.06
     Ultimately
    -0.06
     [].
    -0.06
     televis
    -0.06
    POSITIVE LOGITS
    SPARENT
    0.07
    niční
    0.07
    lararası
    0.07
     Şampiyon
    0.07
    Framework
    0.06
     flaming
    0.06
     Hitch
    0.06
     Wochen
    0.06
     ö
    0.06
     Сер
    0.06
    Act Density 0.040%

    No Known Activations