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

    Neuronpedia

    INDEX
    Explanations

    does

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -helper
    -0.07
     sı
    -0.07
    스트
    -0.06
    .bulk
    -0.06
     asset
    -0.06
     سبب
    -0.06
    /#{
    -0.06
    言葉
    -0.06
     Scr
    -0.06
     Fraser
    -0.06
    POSITIVE LOGITS
    Difficulty
    0.07
     nephew
    0.07
     khối
    0.07
    reason
    0.07
     vc
    0.06
     hlavně
    0.06
     polished
    0.06
    ников
    0.06
     stagn
    0.06
    Prices
    0.06
    Act Density 0.001%

    No Known Activations