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

    Neuronpedia

    INDEX
    Explanations

    check

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vast
    -0.08
    (["
    -0.08
     progressively
    -0.07
     don
    -0.07
    don
    -0.07
     dap
    -0.07
     progress
    -0.07
    ao
    -0.07
     કલ
    -0.07
     utiles
    -0.07
    POSITIVE LOGITS
     überprüfen
    0.09
    orrer
    0.09
     проверить
    0.09
    绍
    0.08
    考虑
    0.08
    《关于
    0.08
     rounding
    0.08
     nuance
    0.08
    .Serialization
    0.08
     regarding
    0.08
    Act Density 0.072%

    No Known Activations