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

    Neuronpedia

    INDEX
    Explanations

    reporting speech or quotes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Transforming
    0.34
     there
    0.32
    IM
    0.30
     Quality
    0.30
     athletes
    0.29
    ਸੀਂ
    0.29
    有些人
    0.29
     Brexit
    0.29
     that
    0.28
     players
    0.28
    POSITIVE LOGITS
    라는
    0.41
     svojoj
    0.35
     अक्टूबर
    0.34
    说道
    0.34
     असते
    0.34
     cười
    0.34
     इनटू
    0.34
    Ꮺ
    0.33
    នៅក្នុង
    0.33
     në
    0.33
    Act Density 0.000%

    No Known Activations