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

    Neuronpedia

    INDEX
    Explanations

    Computer code

    np_max-act · gemini-2.0-flash

    This neuron fires on floating-point numeric literals.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .cells
    -0.07
    ($"
    -0.06
    vendor
    -0.06
     nepří
    -0.06
    .new
    -0.06
    _del
    -0.06
    ителя
    -0.06
    ?=.*
    -0.06
     начинает
    -0.06
     подоб
    -0.06
    POSITIVE LOGITS
     Wales
    0.07
     taş
    0.06
     Awake
    0.06
     Gir
    0.06
    ENS
    0.06
    الث
    0.06
    имв
    0.06
    appa
    0.06
     Traff
    0.06
     sonrası
    0.06
    Act Density 0.344%

    No Known Activations