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
    11
    -0.07
     وزن
    -0.07
    .layouts
    -0.06
     imposs
    -0.06
    12
    -0.06
    _CONVERT
    -0.06
     nu
    -0.06
    .NULL
    -0.06
     troops
    -0.06
    onymous
    -0.06
    POSITIVE LOGITS
    }&
    0.09
    &s
    0.08
    爱
    0.07
     André
    0.07
     шах
    0.07
     와
    0.07
    ossip
    0.07
     '&
    0.07
    (per
    0.07
     Andrea
    0.07
    Act Density 0.031%

    No Known Activations