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

    Neuronpedia

    INDEX
    Explanations

    Time periods

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     LoginPage
    -0.07
     precipitation
    -0.07
     sıra
    -0.07
    stoup
    -0.07
    _manual
    -0.06
    投注
    -0.06
    ad
    -0.06
    uw
    -0.06
    bjerg
    -0.06
    enu
    -0.06
    POSITIVE LOGITS
    [column
    0.07
    '],$_
    0.06
     vf
    0.06
    ;:
    0.06
     là
    0.06
    .BASELINE
    0.06
    ('=
    0.06
    슴
    0.06
     erot
    0.06
    stitutions
    0.06
    Act Density 0.059%

    No Known Activations