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

    Neuronpedia

    INDEX
    Explanations

    title

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .util
    -0.07
     captain
    -0.07
    -0.07
     most
    -0.07
     Drill
    -0.07
     maneuvers
    -0.07
     leans
    -0.06
    My
    -0.06
    .method
    -0.06
     Driver
    -0.06
    POSITIVE LOGITS
     біл
    0.07
     (::
    0.07
     */
↵
↵
↵
    0.07
     Category
    0.06
    _MSG
    0.06
     xứ
    0.06
    "."
    0.06
    っき
    0.06
    /&
    0.06
    <g
    0.06
    Act Density 0.007%

    No Known Activations