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

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     '"
    -0.06
    Opaque
    -0.06
    acman
    -0.06
    ('"
    -0.06
     pickups
    -0.06
     correlates
    -0.06
    는데
    -0.06
    ます
    -0.06
    ensagem
    -0.06
    さら
    -0.06
    POSITIVE LOGITS
    utenant
    0.07
    ナ
    0.07
    ellant
    0.06
     PUBLIC
    0.06
    987
    0.06
     misd
    0.06
    uclear
    0.06
    solve
    0.06
    _tA
    0.06
    (in
    0.06
    Act Density 0.000%

    No Known Activations