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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     лечение
    -0.07
    .course
    -0.07
    Uber
    -0.07
    ירוע
    -0.07
    Meeting
    -0.07
     confined
    -0.07
     Intelligent
    -0.07
    здание
    -0.07
     Naughty
    -0.07
     가지고
    -0.07
    POSITIVE LOGITS
     ordin
    0.07
     ||
↵
    0.07
    `,
    0.06
    rais
    0.06
    /sidebar
    0.06
     continua
    0.06
    日起
    0.06
    ...
↵
    0.06
    tek
    0.06
    悲
    0.06
    Act Density 0.010%

    No Known Activations