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

    Neuronpedia

    INDEX
    Explanations

    goals, assumptions, results

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    坏
    -0.07
    _failed
    -0.07
    ('=
    -0.07
    (img
    -0.07
     جو
    -0.07
    ência
    -0.06
    (table
    -0.06
    邪
    -0.06
     αρι
    -0.06
     자료
    -0.06
    POSITIVE LOGITS
    ="/"
    0.06
     Trotsky
    0.06
     Aş
    0.06
     PyErr
    0.06
     xOffset
    0.06
     UAE
    0.06
     fracking
    0.06
     İlk
    0.06
    _pal
    0.06
    ctrine
    0.05
    Act Density 0.203%

    No Known Activations