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

    Neuronpedia

    INDEX
    Explanations

    optional

    np_max-act · gemini-2.0-flash

    The neuron activates on markers of optional steps in instruction lists—that is, the “optional” label (and its variants) in parenthetical notes.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ribly
    -0.07
    归
    -0.06
    pid
    -0.06
    -temp
    -0.06
     Göz
    -0.06
    协
    -0.06
     маши
    -0.06
    urable
    -0.06
    _logout
    -0.06
     소리
    -0.06
    POSITIVE LOGITS
     ú
    0.07
    _hover
    0.07
    bounding
    0.07
     donate
    0.06
    =False
    0.06
    né
    0.06
     inject
    0.06
    丝
    0.06
     geometry
    0.06
    цией
    0.06
    Act Density 0.038%

    No Known Activations