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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    SETS
    -0.27
    ัย
    -0.26
    eree
    -0.25
    iola
    -0.25
    dy
    -0.25
    Drawable
    -0.24
    ynos
    -0.24
    icity
    -0.24
    ëĵIJ
    -0.24
    itm
    -0.23
    POSITIVE LOGITS
    åĩī
    0.26
     horizon
    0.26
    /schema
    0.26
     Hatch
    0.25
    endez
    0.25
    hor
    0.24
    antic
    0.24
     stream
    0.24
    æĩ
    0.24
     coronavirus
    0.24
    Act Density 2.198%

    No Known Activations