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

    Neuronpedia

    INDEX
    Explanations

    after words from different languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     знаю
    0.92
     :/
    0.88
     secondNumber
    0.85
     lately
    0.85
     కూడా
    0.85
     també
    0.85
     وكذلك
    0.83
     beetje
    0.83
     <!
    0.83
     അതു
    0.83
    POSITIVE LOGITS
    Após
    0.73
    après
    0.73
    Beim
    0.73
    군
    0.71
    የ
    0.71
    Οι
    0.70
    다음
    0.70
     nach
    0.70
    Post
    0.69
    After
    0.68
    Act Density 0.000%

    No Known Activations