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

    Neuronpedia

    INDEX
    Explanations

    Code/Data structures

    np_max-act · gemini-2.0-flash

    The neuron flags floating-point numeric literals (decimal numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Stored
    -0.07
     kB
    -0.07
    -role
    -0.06
    /GPL
    -0.06
    quipment
    -0.06
     premises
    -0.06
    ated
    -0.06
     加
    -0.06
    ดง
    -0.06
    /cli
    -0.06
    POSITIVE LOGITS
     PodsDummy
    0.07
    Rom
    0.06
     SECRET
    0.06
    FAILED
    0.06
     stringBuilder
    0.06
     sense
    0.06
    一个
    0.06
     vod
    0.06
    (socket
    0.06
     púb
    0.06
    Act Density 0.434%

    No Known Activations