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

    Neuronpedia

    INDEX
    Explanations

    tables

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     beginners
    -0.10
     parejas
    -0.09
    Chez
    -0.09
    Beg
    -0.08
     Beginners
    -0.08
    Ман
    -0.08
    Brace
    -0.08
     प्य
    -0.08
     picky
    -0.08
     intu
    -0.08
    POSITIVE LOGITS
     commend
    0.13
     удалось
    0.12
     satisfactory
    0.12
     achievements
    0.12
    此次
    0.12
     accomplishments
    0.12
    成果
    0.11
    Achievements
    0.11
     accomplishment
    0.11
    进行了
    0.10
    Act Density 0.047%

    No Known Activations