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

    Neuronpedia

    INDEX
    Explanations

    instructions

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on imperative action verbs (e.g. “Go,” “Visit,” “Attend,” “Try”) that introduce a suggested challenge or command.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     yếu
    -0.09
     伊
    -0.07
    nea
    -0.06
    -with
    -0.06
    .legend
    -0.06
    urement
    -0.06
     delet
    -0.06
    ίας
    -0.06
     first
    -0.06
     기타
    -0.06
    POSITIVE LOGITS
    -job
    0.06
    {j
    0.06
     Εκ
    0.06
    -theme
    0.06
    arl
    0.06
     Titles
    0.06
    _OBS
    0.06
    _COMPILE
    0.06
     Vous
    0.06
    TestId
    0.06
    Act Density 0.012%

    No Known Activations