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

    Neuronpedia

    INDEX
    Explanations

    where

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     verbonden
    -0.08
    __.
    -0.07
     Valk
    -0.07
    song
    -0.07
    ipur
    -0.07
    _VOID
    -0.07
     периода
    -0.07
    истон
    -0.07
     अलग
    -0.07
    Horiz
    -0.07
    POSITIVE LOGITS
     đúng
    0.11
     tepat
    0.10
     richtigen
    0.10
     sesuai
    0.09
     المناسب
    0.09
     appropriate
    0.09
     нуж
    0.09
    appropriate
    0.09
    正确
    0.09
     adéqu
    0.09
    Act Density 0.062%

    No Known Activations