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

    Neuronpedia

    INDEX
    Explanations

    Chinese pronunciation guide

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     كوساين
    0.32
    Ended
    0.30
    ंमध्ये
    0.30
     مسائل
    0.30
     बिकॉज
    0.30
    👗
    0.29
    ktCap
    0.29
    몄
    0.29
     టిప్పు
    0.29
    ানুভূতি
    0.29
    POSITIVE LOGITS
    0.40
     pronunciation
    0.35
    la
    0.35
     j
    0.34
     Ã
    0.33
    <0xE1>
    0.32
     "
    0.32
     k
    0.32
     n
    0.31
     v
    0.31
    Act Density 0.167%

    No Known Activations