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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ೀಕ್ಷ
    -0.08
    atic
    -0.08
     Bars
    -0.07
     Müller
    -0.07
     ***
    -0.07
    Bars
    -0.07
     программ
    -0.07
    بر
    -0.07
     hrane
    -0.07
    wig
    -0.07
    POSITIVE LOGITS
    ીઓને
    0.09
     khỏi
    0.08
    ส่วน
    0.08
     સમજ
    0.08
     দিয়ে
    0.08
     wote
    0.08
    ใ
    0.08
     nuanced
    0.08
     bairros
    0.08
     fallout
    0.08
    Act Density 0.000%

    No Known Activations