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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    èĢĺ
    -0.27
    ÃŃm
    -0.27
    亮
    -0.25
    URL
    -0.25
    éĴĪ对æĢ§
    -0.24
    ndo
    -0.24
     bin
    -0.24
    ç©¿éĢı
    -0.24
     both
    -0.23
     Both
    -0.23
    POSITIVE LOGITS
    ynos
    0.29
    stag
    0.28
    cac
    0.27
    brane
    0.25
    apo
    0.25
    rene
    0.25
    åįķ车
    0.25
    åľ¨æĪijåĽ½
    0.24
    fare
    0.24
    aise
    0.24
    Act Density 0.019%

    No Known Activations