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

    Neuronpedia

    INDEX
    Explanations

    Consistent Communication / Current Standard

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝙥
    0.48
    ការព
    0.45
    parseLong
    0.45
    íce
    0.45
    ிரிய
    0.44
    adjustable
    0.44
     ಅವನು
    0.43
    ';"+
    0.42
     језик
    0.42
     குளிர்
    0.42
    POSITIVE LOGITS
    ,
    0.51
     (“
    0.50
     alias
    0.49
     (
    0.49
     tap
    0.45
     report
    0.45
     ("
    0.45
     Wine
    0.45
     or
    0.44
     taps
    0.44
    Act Density 0.001%

    No Known Activations