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

    Neuronpedia

    INDEX
    Explanations

    business and work accomplishment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     wry
    0.60
     forment
    0.50
    €˜
    0.49
     �
    0.48
    緍
    0.47
     literally
    0.46
     soooo
    0.46
     --
    0.46
     ½
    0.46
     insure
    0.46
    POSITIVE LOGITS
     subpar
    0.60
    ًا
    0.59
     تقریباً
    0.57
     asimismo
    0.52
    ᵉ
    0.50
     యొక్క
    0.48
     ​​
    0.48
     hingegen
    0.48
     Shayari
    0.47
     yalnızca
    0.47
    Act Density 0.005%

    No Known Activations