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

    Neuronpedia

    INDEX
    Explanations

    Introducing or starting something

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    973
    -0.07
    [@"
    -0.07
    562
    -0.06
     المح
    -0.06
    .do
    -0.06
    Thus
    -0.06
    masked
    -0.06
    ете
    -0.06
     Scoped
    -0.06
     elucid
    -0.06
    POSITIVE LOGITS
     Eddie
    0.07
    (&_
    0.07
     dalam
    0.07
     못
    0.06
     {_
    0.06
     goalie
    0.06
    _UNDER
    0.06
     männ
    0.06
     fate
    0.06
    linik
    0.06
    Act Density 0.150%

    No Known Activations