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

    Neuronpedia

    INDEX
    Explanations

    regional variations and practical usage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ர
    0.46
    elligent
    0.43
    imple
    0.43
    ного
    0.41
     생산
    0.41
    ्य
    0.41
    conder
    0.40
    ส่วน
    0.39
    г
    0.39
     wherever
    0.39
    POSITIVE LOGITS
     amateurs
    0.49
     lads
    0.48
     kul
    0.47
     kev
    0.46
     boys
    0.45
     buf
    0.45
     jurid
    0.45
     amat
    0.45
     kun
    0.44
     polici
    0.44
    Act Density 0.003%

    No Known Activations