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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Jefus
    -0.68
    ंदीखरीदारी
    -0.66
    wiſe
    -0.65
     Majefty
    -0.65
    ſelves
    -0.64
    таратура
    -0.63
     chi̍t
    -0.62
     whoſe
    -0.61
     ſeveral
    -0.61
    ſelf
    -0.61
    POSITIVE LOGITS
     NSCoder
    0.65
    transQ
    0.57
     незавершена
    0.47
    NewReader
    0.46
    phrine
    0.46
    PageRoute
    0.45
     frow
    0.45
    AutoScale
    0.45
    OGND
    0.45
    akka
    0.42
    Act Density 0.001%

    No Known Activations