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

    Neuronpedia

    INDEX
    Explanations

    no

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ®
    -0.07
    trip
    -0.06
     플레이
    -0.06
    _devices
    -0.06
     deadlines
    -0.06
    Literal
    -0.06
    Usually
    -0.06
    裏
    -0.06
     usually
    -0.06
    _EXISTS
    -0.06
    POSITIVE LOGITS
     no
    0.08
     vám
    0.07
     Sig
    0.07
    Comic
    0.06
     dog
    0.06
    QDebug
    0.06
     gì
    0.06
    _void
    0.06
     ming
    0.06
     anytime
    0.06
    Act Density 0.013%

    No Known Activations