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

    Neuronpedia

    INDEX
    Explanations

    geometrical relationships

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    最高
    -0.08
    ape
    -0.08
     savings
    -0.08
     Fidel
    -0.08
     shel
    -0.08
     coerc
    -0.07
     mythology
    -0.07
     wrapped
    -0.07
    اتي
    -0.07
    Air
    -0.07
    POSITIVE LOGITS
     પાસે
    0.10
     perpendicular
    0.10
     intersects
    0.09
    Intersect
    0.09
     sticks
    0.09
    .Direction
    0.09
     некоторое
    0.08
    Stick
    0.08
     Rays
    0.08
     Kry
    0.08
    Act Density 0.012%

    No Known Activations