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

    Neuronpedia

    INDEX
    Explanations

    sports standings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     widths
    -0.06
    Du
    -0.06
    57
    -0.06
     Ironically
    -0.06
     psychotic
    -0.06
    zn
    -0.06
     riêng
    -0.06
    ’ye
    -0.06
    [o
    -0.06
    thanks
    -0.06
    POSITIVE LOGITS
     fray
    0.08
    عار
    0.07
     говор
    0.07
    .setVerticalGroup
    0.07
     damning
    0.07
    prompt
    0.07
    _Message
    0.06
    /original
    0.06
     projected
    0.06
    (Rect
    0.06
    Act Density 0.014%

    No Known Activations