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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Generic
    -0.07
    úng
    -0.06
    lish
    -0.06
    θή
    -0.06
     ﾘ
    -0.06
     расход
    -0.06
    ůž
    -0.06
    FileManager
    -0.06
     vết
    -0.06
     Apprentice
    -0.06
    POSITIVE LOGITS
     Interviews
    0.07
    ATIONS
    0.06
     hydro
    0.06
     realise
    0.06
     Scenes
    0.06
    elin
    0.06
     discourse
    0.06
     PORT
    0.06
    ][
    0.06
     -.
    0.06
    Act Density 0.088%

    No Known Activations