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

    Neuronpedia

    INDEX
    Explanations

    machine/hex code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    badge
    -0.07
     bra
    -0.07
     Brown
    -0.06
    preter
    -0.06
     imposs
    -0.06
     Titans
    -0.06
    .scenes
    -0.06
    раст
    -0.06
     فق
    -0.06
    locker
    -0.06
    POSITIVE LOGITS
    (JNIEnv
    0.09
    .Elapsed
    0.08
     Erie
    0.07
    (separator
    0.07
     YYS
    0.06
     [&
    0.06
    _mac
    0.06
    isser
    0.06
     PowerPoint
    0.06
    ）。
    0.06
    Act Density 0.008%

    No Known Activations