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

    Neuronpedia

    INDEX
    Explanations

    libraries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     convey
    -0.07
    竞赛
    -0.07
     Oswald
    -0.07
    营
    -0.07
     cerv
    -0.06
     Hemp
    -0.06
     comprises
    -0.06
     particular
    -0.06
     tram
    -0.06
    一篇
    -0.06
    POSITIVE LOGITS
    .change
    0.08
     racial
    0.07
    ligne
    0.07
    Maria
    0.07
     joking
    0.07
    _scaling
    0.07
     births
    0.07
    amples
    0.07
    Leaders
    0.07
    ivors
    0.07
    Act Density 0.047%

    No Known Activations