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

    Neuronpedia

    INDEX
    Explanations

    foundational concepts and questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bounces
    0.49
     bumps
    0.42
     muchas
    0.42
    ः
    0.42
    NEED
    0.42
    很多
    0.41
    ness
    0.41
    famous
    0.41
    ibre
    0.41
    lide
    0.41
    POSITIVE LOGITS
     свар
    0.49
     изпол
    0.47
    ਠ
    0.44
     стратеги
    0.44
     תח
    0.44
     ENGINEER
    0.43
     GameObject
    0.42
    GameObject
    0.42
     CHAIRMAN
    0.41
     реализации
    0.40
    Act Density 0.005%

    No Known Activations