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

    Neuronpedia

    INDEX
    Explanations

    say "ino" ending

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    агыла
    -0.09
    аре
    -0.09
    оратив
    -0.09
    τροφ
    -0.09
    АР
    -0.08
    тады
    -0.08
    Ар
    -0.08
    стройство
    -0.08
     Cosmetics
    -0.08
    истрация
    -0.08
    POSITIVE LOGITS
    ino
    0.16
    inos
    0.13
    INO
    0.12
     chess
    0.08
     domino
    0.08
    imension
    0.08
     flipped
    0.07
     Viz
    0.07
    im
    0.07
    imos
    0.07
    Act Density 0.001%

    No Known Activations