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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash

    The neuron flags floating‐point numeric literals (numbers with decimal points) in the code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    /Grid
    -0.07
     Upon
    -0.06
    kového
    -0.06
    猛
    -0.06
    054
    -0.06
    SerializeField
    -0.06
    �
    -0.06
    /dashboard
    -0.06
    _pe
    -0.06
    303
    -0.06
    POSITIVE LOGITS
     Kor
    0.07
     pork
    0.06
     laz
    0.06
    ellan
    0.06
    deposit
    0.06
     Jersey
    0.06
    ินทาง
    0.06
     Reserved
    0.06
    ælland
    0.06
     ambition
    0.06
    Act Density 0.027%

    No Known Activations