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

    Neuronpedia

    INDEX
    Explanations

    describes specifics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     visage
    0.41
    দ্দিন
    0.39
     공부해
    0.39
     doch
    0.39
     لیکن
    0.38
     figlio
    0.38
    瑾
    0.38
     livid
    0.38
    кович
    0.37
     також
    0.37
    POSITIVE LOGITS
    ers
    0.50
    party
    0.45
    The
    0.44
    ători
    0.44
    format
    0.43
     Credit
    0.43
    6
    0.42
    Credit
    0.42
    人民币
    0.42
    erial
    0.42
    Act Density 0.010%

    No Known Activations