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

    Neuronpedia

    INDEX
    Explanations

    first point introduction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     również
    0.56
     রি
    0.53
     ALSO
    0.50
     αυτή
    0.46
    也能
    0.46
     även
    0.46
     ankaŭ
    0.45
     altri
    0.45
     både
    0.44
     also
    0.44
    POSITIVE LOGITS
     positiva
    0.53
    the
    0.52
     спасибо
    0.48
    there
    0.46
    ،
    0.45
     समझिए
    0.45
    s
    0.43
    ၊
    0.42
    ства
    0.42
    考慮
    0.42
    Act Density 0.029%

    No Known Activations