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

    Neuronpedia

    INDEX
    Explanations

    Planes and intersections

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dividends
    -0.09
     cyfr
    -0.08
    .'.
    -0.08
    .calls
    -0.08
     outsourced
    -0.08
    ARGV
    -0.08
     رضي
    -0.08
    >>,
    -0.08
     molinos
    -0.08
     withdrawals
    -0.08
    POSITIVE LOGITS
     wedge
    0.08
     Kinect
    0.08
    0.08
    组三
    0.08
    imu
    0.08
     trid
    0.08
    pendicular
    0.08
     terceira
    0.08
    planes
    0.08
    -horizontal
    0.07
    Act Density 0.019%
    No Known Activations