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

    Neuronpedia

    INDEX
    Explanations

    as

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Clipboard
    -0.07
    Canon
    -0.06
    верд
    -0.06
    约
    -0.06
     skeptic
    -0.06
    atu
    -0.06
    自由
    -0.06
     مشکل
    -0.06
     Championship
    -0.06
     seul
    -0.06
    POSITIVE LOGITS
    Lisa
    0.08
    werp
    0.08
     Lisa
    0.07
    (bus
    0.07
    rous
    0.07
     MSE
    0.07
     including
    0.07
     ascertain
    0.07
    еса
    0.07
    =row
    0.07
    Act Density 0.030%

    No Known Activations