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

    Neuronpedia

    INDEX
    Explanations

    legality

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    student
    -0.07
    (area
    -0.07
    MLE
    -0.07
     Philadelphia
    -0.07
    澳大
    -0.06
    𝘠
    -0.06
    Labor
    -0.06
    없
    -0.06
    ԓ
    -0.06
     Guards
    -0.06
    POSITIVE LOGITS
    此案
    0.08
    adows
    0.08
    'in
    0.07
    美味
    0.07
    ól
    0.07
    -bot
    0.07
     cropped
    0.07
     distressed
    0.07
    -script
    0.07
     där
    0.07
    Act Density 0.023%

    No Known Activations