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

    Neuronpedia

    INDEX
    Explanations

    questions and answers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _subs
    -0.07
    -actions
    -0.07
    (ad
    -0.07
     institute
    -0.06
    КИ
    -0.06
    TECTED
    -0.06
     conquest
    -0.06
    Ads
    -0.06
     开始
    -0.06
    Demand
    -0.06
    POSITIVE LOGITS
    秘
    0.07
     exploding
    0.07
     opráv
    0.06
    ีป
    0.06
    วไป
    0.06
    ョ
    0.06
    ("-",
    0.06
     MemoryStream
    0.06
    严
    0.06
    ュ
    0.06
    Act Density 0.072%

    No Known Activations