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

    Neuronpedia

    INDEX
    Explanations

    police

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    した
    -0.06
    개월
    -0.06
    یدا
    -0.06
     Tulsa
    -0.06
     Haskell
    -0.06
    <object
    -0.06
     temporary
    -0.06
    诉
    -0.06
    δης
    -0.06
     dreamed
    -0.06
    POSITIVE LOGITS
    ινε
    0.08
     Police
    0.07
    .expand
    0.06
     Forces
    0.06
    icina
    0.06
     Humph
    0.06
     Ради
    0.06
    verte
    0.06
    %↵↵
    0.06
     佐
    0.06
    Act Density 0.007%

    No Known Activations