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

    Neuronpedia

    INDEX
    Explanations

    C++ code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    gramModel
    0.35
    >");
    0.34
     furtherance
    0.34
    fluoro
    0.32
     мальчика
    0.32
    Posture
    0.31
     }}=\
    0.31
    ждую
    0.31
     বাজে
    0.30
     prawidł
    0.30
    POSITIVE LOGITS
    ios
    0.38
     annul
    0.30
     sareng
    0.30
    ՝
    0.29
    system
    0.29
     {
    0.29
    يف
    0.29
    iosos
    0.28
     suspe
    0.28
    cou
    0.28
    Act Density 0.009%

    No Known Activations