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

    Neuronpedia

    INDEX
    Explanations

    Odd length cycles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     predictive
    -0.08
     Lara
    -0.08
     Wasi
    -0.08
     DIGITAL
    -0.08
     ypos
    -0.08
     cloudy
    -0.08
     paranormal
    -0.07
     cientí
    -0.07
     Legendary
    -0.07
     PERSONAL
    -0.07
    POSITIVE LOGITS
     shortest
    0.10
     shorter
    0.10
    Shortest
    0.10
    -length
    0.09
     lengths
    0.09
     annul
    0.09
    -Length
    0.09
     läng
    0.09
     length
    0.09
     longer
    0.09
    Act Density 0.007%

    No Known Activations