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

    Neuronpedia

    INDEX
    Explanations

    code blocks and html tags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    車の
    0.48
    ເພ
    0.47
    옷
    0.47
    Car
    0.47
    승
    0.47
    ඖ
    0.46
    ර්ධ
    0.46
     ulterior
    0.45
    황
    0.45
    ጨም
    0.44
    POSITIVE LOGITS
     palliative
    0.43
     subdivisions
    0.43
     forfeiture
    0.42
    err
    0.41
     div
    0.41
    უ
    0.41
    eggi
    0.41
     kur
    0.41
     সার্ব
    0.41
     subdivided
    0.41
    Act Density 0.001%

    No Known Activations