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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     DataContext
    -0.07
    .Unsupported
    -0.06
    なる
    -0.06
     landscapes
    -0.06
     çözüm
    -0.06
     lik
    -0.06
     squad
    -0.06
     liar
    -0.06
    avatars
    -0.06
    "Oh
    -0.06
    POSITIVE LOGITS
    .linkedin
    0.07
    _sig
    0.07
     пере
    0.07
     tin
    0.06
    Sin
    0.06
     Lesson
    0.06
    oto
    0.06
    [to
    0.06
     sin
    0.06
    _RAM
    0.06
    Act Density 0.001%

    No Known Activations