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

    Neuronpedia

    INDEX
    Explanations

    documentation examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    پ
    0.54
    هي
    0.48
    તે
    0.47
    日本の
    0.46
    Luego
    0.45
    ال
    0.45
    দৈ
    0.44
    <h3>
    0.44
    平成
    0.44
    বাংলাদেশের
    0.44
    POSITIVE LOGITS
    TZ
    0.45
     몰
    0.44
    kowe
    0.43
     посмотреть
    0.42
    kaz
    0.41
     DSO
    0.41
    chette
    0.40
    kow
    0.40
     waardoor
    0.40
     původ
    0.40
    Act Density 0.003%

    No Known Activations