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

    Neuronpedia

    INDEX
    Explanations

    here are examples or instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ದು
    0.46
    кою
    0.44
     അടുത്ത
    0.42
    σή
    0.42
     resentment
    0.41
     Ll
    0.40
    amani
    0.40
     another
    0.40
    ﻌ
    0.39
     ',
    0.39
    POSITIVE LOGITS
    ล้ว
    0.37
    University
    0.36
     중심
    0.35
    ंख्य
    0.35
    Electron
    0.35
    Alcohol
    0.34
    الب
    0.34
     âg
    0.34
     транспо
    0.33
     ചെയ്യുന്നത്
    0.33
    Act Density 0.008%

    No Known Activations