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

    Neuronpedia

    INDEX
    Explanations

    technical/engineering

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of the technical term “flow,” particularly in reference to fluid‐flow contexts.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    極
    -0.07
    -Tr
    -0.07
    ftar
    -0.06
     Centers
    -0.06
    采
    -0.06
    unist
    -0.06
    _ERROR
    -0.06
     Aircraft
    -0.06
     truyền
    -0.06
    資
    -0.06
    POSITIVE LOGITS
    _mm
    0.07
    .pic
    0.07
    BBBB
    0.07
    ıc
    0.06
    िसक
    0.06
    **************
    0.06
    |;↵
    0.06
    .left
    0.06
    (lua
    0.06
    Margin
    0.06
    Act Density 0.715%

    No Known Activations