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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    windows
    -0.07
     takže
    -0.07
    ันเป
    -0.07
    Tile
    -0.07
    ="./
    -0.06
     spending
    -0.06
     upbringing
    -0.06
     diesen
    -0.06
    (stage
    -0.06
     manners
    -0.06
    POSITIVE LOGITS
     اصول
    0.06
    prus
    0.06
    الإ
    0.06
    ramids
    0.06
    Rightarrow
    0.06
    raph
    0.06
     tg
    0.06
     уд
    0.06
    IFE
    0.05
    oret
    0.05
    Act Density 0.000%

    No Known Activations