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

    Neuronpedia

    INDEX
    Explanations

    units of measurements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ग़
    0.94
     aisément
    0.93
     सगळे
    0.88
    뎌
    0.86
    мою
    0.86
     कोई
    0.85
    ተት
    0.85
     nggak
    0.84
    ඵ
    0.84
     tenets
    0.83
    POSITIVE LOGITS
     XNUMX
    1.46
     ("
    1.41
     ().
    1.32
     (),
    1.30
     /
    1.27
     ​​
    1.26
    NUMX
    1.22
     ()
    1.20
     "".
    1.20
     "",
    1.19
    Act Density 0.007%

    No Known Activations