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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Robertson
    -0.07
     distinctly
    -0.07
    rior
    -0.06
    oru
    -0.06
     Sonra
    -0.06
     Kata
    -0.06
     resemblance
    -0.06
     hal
    -0.06
     Significant
    -0.06
     bounding
    -0.06
    POSITIVE LOGITS
     handc
    0.07
    深圳
    0.07
    (theta
    0.07
    溫
    0.07
     phóng
    0.07
    =int
    0.06
     Mek
    0.06
     mum
    0.06
    啦
    0.06
    bnb
    0.06
    Act Density 0.002%

    No Known Activations