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

    Neuronpedia

    INDEX
    Explanations

    non-English text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rétro
    -0.08
     clad
    -0.08
    喜
    -0.08
     ഗുര
    -0.08
     Throws
    -0.07
     நேர
    -0.07
    _versions
    -0.07
     skl
    -0.07
     ज़
    -0.07
    DU
    -0.07
    POSITIVE LOGITS
     firstly
    0.08
     hingegen
    0.07
     semakin
    0.07
     wiederum
    0.07
    elius
    0.07
     aparentemente
    0.07
    依据
    0.07
     likewise
    0.07
     عبارة
    0.07
     invece
    0.07
    Act Density 0.072%

    No Known Activations