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

    Neuronpedia

    INDEX
    Explanations

    web search, neural networks, desert, pet supplies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ebok
    0.40
    лесо
    0.38
    িনিয়ার
    0.37
    ковое
    0.37
     balkon
    0.37
     sehen
    0.37
    리카
    0.37
     possono
    0.36
     lewis
    0.36
    newblock
    0.36
    POSITIVE LOGITS
    Develop
    0.43
    uate
    0.41
    ILL
    0.39
    ۹
    0.39
     मेरा
    0.38
    "
    0.38
     ט
    0.37
    United
    0.37
     बुद्ध
    0.37
    {
    0.37
    Act Density 0.407%

    No Known Activations