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

    Neuronpedia

    INDEX
    Explanations

    }

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    [Z
    -0.07
     Voor
    -0.07
     Zone
    -0.06
    repos
    -0.06
     Jean
    -0.06
     原
    -0.06
    special
    -0.06
     Bush
    -0.06
     grass
    -0.06
     Val
    -0.06
    POSITIVE LOGITS
     Wishlist
    0.07
    usually
    0.07
     Renderer
    0.06
    해요
    0.06
     POSIX
    0.06
    _PAYMENT
    0.06
     getopt
    0.06
     Лі
    0.06
     produk
    0.06
    calar
    0.06
    Act Density 0.001%

    No Known Activations