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

    Neuronpedia

    INDEX
    Explanations

    disclaimers and notes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    不过
    0.91
    ර්ධ
    0.91
    ikko
    0.90
     不是
    0.85
     还
    0.82
     किन्तु
    0.80
    ◜
    0.80
    nfasis
    0.78
    tris
    0.78
    っいて
    0.78
    POSITIVE LOGITS
     end
    0.71
     facing
    0.70
     cụ
    0.69
     Types
    0.68
     End
    0.67
     suck
    0.67
     pitched
    0.65
     forn
    0.62
     eup
    0.62
     Globalization
    0.62
    Act Density 0.012%

    No Known Activations