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

    Neuronpedia

    INDEX
    Explanations

    programming code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     مر
    -0.08
    Andre
    -0.07
    (level
    -0.07
    Revenue
    -0.07
    饫
    -0.07
    גיד
    -0.06
    .Tile
    -0.06
    긁
    -0.06
    ╌
    -0.06
    _minimum
    -0.06
    POSITIVE LOGITS
    '],'
    0.08
     홈
    0.07
    定了
    0.07
    _down
    0.07
    公式
    0.07
    fläche
    0.07
     увели
    0.07
     muttered
    0.07
     Rak
    0.07
    欄
    0.06
    Act Density 0.003%

    No Known Activations