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

    Neuronpedia

    INDEX
    Explanations

    Here

    np_max-act · gemini-2.0-flash

    sentence-initial discourse markers that introduce examples, explanations, or contextual framing.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Negative Logits
    uyện
    -0.07
    AUD
    -0.07
    �
    -0.07
    роз
    -0.06
    zac
    -0.06
    search
    -0.06
    }'
    -0.06
    xs
    -0.06
    ́
    -0.06
    -sale
    -0.06
    POSITIVE LOGITS
    (dm
    0.09
    .maximum
    0.07
     Bulk
    0.07
     carriage
    0.07
    .getSource
    0.06
    (policy
    0.06
     No
    0.06
     Chief
    0.06
     ORM
    0.06
    .It
    0.06
    Act Density 0.290%

    No Known Activations