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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     SUMMARY
    -0.06
    ServiceImpl
    -0.06
     khá
    -0.06
    dynamic
    -0.06
    keiten
    -0.06
     Dum
    -0.06
     ssl
    -0.06
     idols
    -0.06
    -review
    -0.06
     suce
    -0.06
    POSITIVE LOGITS
    ,double
    0.07
    @Repository
    0.06
    erv
    0.06
    iedad
    0.06
    (blob
    0.06
    ्रश
    0.06
     самой
    0.06
    阶
    0.06
    Guid
    0.06
     특히
    0.06
    Act Density 0.030%

    No Known Activations