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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions with currency symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
      
    1.57
       
    1.22
    YOUR
    1.15
    Your
    1.10
     (‘
    1.10
     *
    1.09
     ＊
    1.09
    あなた
    1.08
     ‘
    1.08
    ‑
    1.07
    POSITIVE LOGITS
     $\{
    1.65
     $\
    1.62
     $
    1.58
     $-
    1.48
     $\$
    1.38
     $(
    1.37
     $|
    1.36
     $-\
    1.32
     $(\
    1.31
     $=
    1.30
    Act Density 0.474%

    No Known Activations