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

    Neuronpedia

    INDEX
    Explanations

    existing systems and resources

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    储
    -0.07
    ilen
    -0.07
     Certif
    -0.07
     trò
    -0.07
    .Appearance
    -0.07
     joystick
    -0.06
    .Dispose
    -0.06
     exhausted
    -0.06
    تاب
    -0.06
     出
    -0.06
    POSITIVE LOGITS
     |↵
    0.06
     nám
    0.06
     *****
    0.06
    ancouver
    0.06
     pray
    0.06
    noon
    0.06
    ysterious
    0.06
     Vancouver
    0.06
    itative
    0.06
    buquerque
    0.06
    Act Density 0.047%

    No Known Activations