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

    Neuronpedia

    INDEX
    Explanations

    Debt

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (js
    -0.06
    /contentassist
    -0.06
     BE
    -0.06
     Deutsch
    -0.06
     Tolkien
    -0.06
    discord
    -0.05
    649
    -0.05
     adopted
    -0.05
    -control
    -0.05
    .urlencoded
    -0.05
    POSITIVE LOGITS
    ś
    0.07
     Indians
    0.07
    GetName
    0.07
     subsid
    0.07
     нанес
    0.07
     (↵↵
    0.07
     刘
    0.07
     -.
    0.07
    atile
    0.06
     flagship
    0.06
    Act Density 0.009%

    No Known Activations