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

    Neuronpedia

    INDEX
    Explanations

    how to use

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    用于
    0.38
    r
    0.36
    expenses
    0.35
    ใช้งาน
    0.34
    への
    0.33
    ر
    0.32
    there
    0.32
     Attempts
    0.32
    being
    0.32
    Used
    0.31
    POSITIVE LOGITS
    fully
    0.68
     techniques
    0.62
    fulness
    0.48
     técnicas
    0.46
     caution
    0.46
     principles
    0.45
     only
    0.44
     sparingly
    0.44
     appropriate
    0.42
     преимущества
    0.42
    Act Density 0.171%

    No Known Activations