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

    Neuronpedia

    INDEX
    Explanations

    purpose or function

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     עם
    0.61
     जाणून
    0.48
     utilizzando
    0.46
     serán
    0.46
     ابھی
    0.46
     باستخدام
    0.46
     saranno
    0.44
     sarebbero
    0.44
     estará
    0.44
     придется
    0.44
    POSITIVE LOGITS
     helps
    1.09
     provides
    0.96
     Helps
    0.91
     primarily
    0.89
    的作用
    0.88
     помогает
    0.86
     helping
    0.85
     giúp
    0.85
    用来
    0.85
     functions
    0.84
    Act Density 0.342%

    No Known Activations