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

    Neuronpedia

    INDEX
    Explanations

    prime number checking code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Range
    0.45
    mostly
    0.41
    leaders
    0.39
     প্রযুক্তি
    0.39
     either
    0.38
    差异
    0.37
     regiment
    0.36
    Mga
    0.36
    either
    0.36
     વૃ
    0.36
    POSITIVE LOGITS
     colorectal
    0.42
     உச்ச
    0.38
    ㄒ
    0.38
     crise
    0.37
     broom
    0.37
     bolster
    0.37
     می‌توانید
    0.37
    诏
    0.37
    uros
    0.36
     laik
    0.36
    Act Density 0.001%

    No Known Activations