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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash

    The neuron detects when the text is introducing or labeling example/illustration sections (e.g. “some examples of…”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     ps
    -0.07
    _destination
    -0.07
     workers
    -0.06
    robe
    -0.06
    itle
    -0.06
    ,val
    -0.06
     enabling
    -0.06
    _Show
    -0.06
    .`
    -0.06
    _additional
    -0.06
    POSITIVE LOGITS
     ®
    0.07
    nější
    0.07
     душ
    0.06
     Networking
    0.06
     иму
    0.06
     ابراه
    0.06
    rası
    0.06
     náklad
    0.06
     stmt
    0.06
     ethernet
    0.06
    Act Density 0.017%

    No Known Activations