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

    Neuronpedia

    INDEX
    Explanations

    comprehensive overview

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Using
    0.27
     Tukey
    0.26
     dreaded
    0.25
     我
    0.25
     moſt
    0.25
     $
    0.24
     strategically
    0.24
     Btn
    0.24
     Når
    0.24
    ணமாக
    0.24
    POSITIVE LOGITS
    पणे
    0.45
     nhất
    0.38
     ترین
    0.36
    पणा
    0.34
     للغاية
    0.33
    -
    0.32
     banget
    0.31
    issime
    0.31
     অথচ
    0.30
     albeit
    0.30
    Act Density 4.356%

    No Known Activations