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

    Neuronpedia

    INDEX
    Explanations

    matplotlib.pyplot

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Transactional
    0.38
    元的
    0.38
     snakes
    0.38
     externally
    0.38
     translating
    0.38
    國際
    0.38
     ন্যায
    0.38
     metals
    0.37
     guilt
    0.37
    ம்தான்
    0.37
    POSITIVE LOGITS
     בנו
    0.46
     процен
    0.43
    zz
    0.42
    
    0.41
     поговори
    0.40
     разговор
    0.39
    Sebagai
    0.38
    order
    0.38
    chsler
    0.38
    life
    0.38
    Act Density 0.000%

    No Known Activations