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

    Neuronpedia

    INDEX
    Explanations

    translate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Pun
    -0.06
    Reward
    -0.06
    lland
    -0.06
    Fmt
    -0.06
    继
    -0.06
    .questions
    -0.06
     Raf
    -0.06
     isEqual
    -0.06
     Kur
    -0.06
     Rin
    -0.06
    POSITIVE LOGITS
     correctly
    0.07
     similar
    0.07
     TICK
    0.07
    generator
    0.06
     assaults
    0.06
     čist
    0.06
     incorrectly
    0.06
     ↵		↵
    0.06
     этих
    0.06
     replicate
    0.06
    Act Density 0.009%

    No Known Activations