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

    Neuronpedia

    INDEX
    Explanations

    as a part

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bringen
    0.49
     anyone
    0.49
     வேற
    0.47
     tiz
    0.46
     blinked
    0.46
     woe
    0.46
     heavens
    0.46
     everyone
    0.45
     whoever
    0.45
     behö
    0.44
    POSITIVE LOGITS
    part
    0.73
     part
    0.70
     Part
    0.61
    Part
    0.61
     часть
    0.56
     частью
    0.52
    的一部分
    0.50
     Основ
    0.47
    PART
    0.47
    adata
    0.46
    Act Density 0.060%

    No Known Activations