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

    Neuronpedia

    INDEX
    Explanations

    multilingual concepts and observations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Secrets
    0.53
     রহ
    0.49
     الملك
    0.46
     احسن
    0.44
    ablanca
    0.44
     결과를
    0.44
    The
    0.43
     Від
    0.43
     Secrets
    0.43
    King
    0.42
    POSITIVE LOGITS
    sided
    0.50
    人
    0.49
     उपकरण
    0.49
     оборудование
    0.49
    to
    0.46
    গুলো
    0.46
    ೇನೆ
    0.46
    ுகிறார்கள்
    0.46
    s
    0.46
    sentation
    0.45
    Act Density 0.001%

    No Known Activations