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

    Neuronpedia

    INDEX
    Explanations

    and/or

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ميم
    -0.07
     код
    -0.07
    ालय
    -0.07
     confinement
    -0.07
    iversity
    -0.06
    Theta
    -0.06
     '
    -0.06
    \Test
    -0.06
     залеж
    -0.06
    code
    -0.06
    POSITIVE LOGITS
     Mostly
    0.06
     gdk
    0.06
     Bundy
    0.06
    locs
    0.06
     aren
    0.06
    AGAIN
    0.06
     надо
    0.06
     paradigm
    0.06
    ||(
    0.06
    景
    0.06
    Act Density 0.043%

    No Known Activations