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

    Neuronpedia

    INDEX
    Explanations

    official certification exam guides

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     SalesLT
    0.91
     Lazar
    0.90
     adware
    0.86
    Certified
    0.86
     நூற்றாண்டில்
    0.83
     Cisco
    0.83
    াদক
    0.82
     ACHIE
    0.82
    悧
    0.81
     именно
    0.79
    POSITIVE LOGITS
     :
    0.75
     guide
    0.69
     surge
    0.67
     watch
    0.66
     ربنا
    0.64
    ढ़
    0.63
    参考
    0.62
     वर्ग
    0.61
     hating
    0.61
     ;
    0.61
    Act Density 0.002%

    No Known Activations