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

    Neuronpedia

    INDEX
    Explanations

    Numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    贡献
    -0.07
    央视
    -0.07
    ಗ
    -0.06
    iations
    -0.06
    .Def
    -0.06
    ᠡ
    -0.06
    年以来
    -0.06
    ぎ
    -0.06
    墘
    -0.06
     העסק
    -0.06
    POSITIVE LOGITS
    残
    0.08
     오
    0.07
    0.07
     Ariel
    0.07
    0.07
     blir
    0.07
     Nylon
    0.07
     errs
    0.07
    (par
    0.07
    0.07
    Act Density 0.040%

    No Known Activations