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

    Neuronpedia

    INDEX
    Explanations

    quotation mark

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     compens
    -0.08
     slicing
    -0.08
     syncing
    -0.08
    ಿತ್ತು
    -0.08
     ஆய
    -0.07
     tess
    -0.07
     Mosk
    -0.07
    -0.07
    �
    -0.07
     aforementioned
    -0.07
    POSITIVE LOGITS
    是什么意思
    0.10
     jedhu
    0.09
    什么意思
    0.09
    。我
    0.08
    Subtitle
    0.08
     అనే
    0.08
     Six
    0.08
     refers
    0.08
    amentul
    0.08
     excerpt
    0.08
    Act Density 0.065%
    No Known Activations