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

    Neuronpedia

    INDEX
    Explanations

    Mysore

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    alyptus
    -0.74
    lorette
    -0.58
    TAINMENT
    -0.55
    المناصب
    -0.55
     Twig
    -0.54
    Twig
    -0.54
    ksikon
    -0.53
    lihood
    -0.52
    therford
    -0.52
    cense
    -0.52
    POSITIVE LOGITS
    s
    0.64
    válasz
    0.59
     snippetHide
    0.58
     ujednoznacz
    0.54
    ########.
    0.54
     arché
    0.54
    umbra
    0.53
     ulang
    0.51
     Hickey
    0.51
    heide
    0.50
    Act Density 0.444%

    No Known Activations