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

    Neuronpedia

    INDEX
    Explanations

    words starting with A or P

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Dazu
    -0.78
    🏐
    -0.77
    ету
    -0.74
    дизайн
    -0.73
     מט
    -0.73
     SATA
    -0.73
    Folgende
    -0.72
    擂
    -0.72
    ])[
    -0.72
     Nog
    -0.71
    POSITIVE LOGITS
    君
    0.72
     pickled
    0.71
    有没有
    0.71
    じゅう
    0.71
    兰
    0.69
    Vanjske
    0.68
    França
    0.67
    зма
    0.67
     Smoky
    0.67
    砝
    0.66
    Act Density 0.011%

    No Known Activations