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

    Neuronpedia

    INDEX
    Explanations

    might

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    талған
    -0.08
     കേന്ദ്ര
    -0.08
     Levine
    -0.08
     housed
    -0.08
     sekä
    -0.08
    ട്
    -0.08
     Cecil
    -0.08
    ваюцца
    -0.08
     кров
    -0.08
     Централь
    -0.08
    POSITIVE LOGITS
     unknow
    0.10
     intention
    0.09
     accidentally
    0.09
     intends
    0.09
     muốn
    0.09
     typo
    0.09
     slang
    0.09
     silly
    0.08
     intended
    0.08
     intentions
    0.08
    Act Density 0.045%

    No Known Activations