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

    Neuronpedia

    INDEX
    Explanations

    special characters and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dot
    0.41
     motion
    0.40
     notation
    0.40
     indicated
    0.39
     '.'
    0.39
     unit
    0.38
     fração
    0.38
     плен
    0.38
     space
    0.37
     indicate
    0.37
    POSITIVE LOGITS
     $\#
    0.45
    াশ
    0.44
    \#
    0.44
    سترول
    0.44
     سوشل
    0.43
    覀
    0.42
    Allister
    0.41
    iul
    0.41
    .#
    0.41
     सरफेस
    0.40
    Act Density 0.032%

    No Known Activations