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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash

    This neuron fires on numerical values formatted inside parentheses (e.g. decimal numbers or reference‐style numbers in brackets).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ราช
    -0.07
    ERTICAL
    -0.06
     prescriptions
    -0.06
    ,j
    -0.06
    Flex
    -0.06
    ories
    -0.06
    存于
    -0.06
    Від
    -0.06
     fewer
    -0.06
     pojist
    -0.06
    POSITIVE LOGITS
    UserDefaults
    0.06
     rá
    0.06
     시즌
    0.06
    EntryPoint
    0.06
     Interrupt
    0.06
    .gravity
    0.06
    웨어
    0.06
     LV
    0.05
     Ú
    0.05
    вод
    0.05
    Act Density 0.021%

    No Known Activations