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

    Neuronpedia

    INDEX
    Explanations

    -g

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mö
    -0.07
    /site
    -0.07
    Sparse
    -0.07
    靺
    -0.07
    𬭁
    -0.06
     Det
    -0.06
    )sender
    -0.06
    摅
    -0.06
     volver
    -0.06
     Lol
    -0.06
    POSITIVE LOGITS
    _mean
    0.08
    攻势
    0.08
    Components
    0.08
     полож
    0.08
    玩法
    0.07
    姿态
    0.07
    问题
    0.07
    _DB
    0.07
     carbs
    0.07
     chemicals
    0.07
    Act Density 0.001%

    No Known Activations