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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    {
↵
    -0.07
     moll
    -0.07
    |,↵
    -0.06
     filho
    -0.06
    ，他们
    -0.06
    .ads
    -0.06
    陶
    -0.06
     Someone
    -0.06
    ۷
    -0.06
    },
↵
    -0.06
    POSITIVE LOGITS
     physician
    0.07
    -datepicker
    0.06
     необходим
    0.06
    -mult
    0.06
     recognition
    0.06
     Insp
    0.06
    ichick
    0.06
    GameState
    0.06
    _refresh
    0.06
    рим
    0.06
    Act Density 0.015%

    No Known Activations