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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     websites
    -0.08
     subway
    -0.07
     Edge
    -0.07
    HeadersHeight
    -0.06
     plausible
    -0.06
    bike
    -0.06
    -three
    -0.06
    这些
    -0.06
    site
    -0.06
    into
    -0.06
    POSITIVE LOGITS
     hayır
    0.07
     Contributions
    0.06
     amalg
    0.06
     flo
    0.06
     )(
    0.06
     arbitr
    0.06
    urt
    0.06
    _weather
    0.06
    pun
    0.06
    (gen
    0.06
    Act Density 0.038%

    No Known Activations