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

    Neuronpedia

    INDEX
    Explanations

    general English writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _TRUE
    -0.08
     wildlife
    -0.08
    .getWorld
    -0.08
    ɩ
    -0.07
    虽
    -0.07
    耸
    -0.07
    ประชาชน
    -0.07
    ساء
    -0.07
     &&↵
    -0.07
     algún
    -0.07
    POSITIVE LOGITS
    ../
    0.08
    Updater
    0.08
    >K
    0.07
    ="">
    0.07
     Aer
    0.07
     tarea
    0.07
    }catch
    0.07
     ImageButton
    0.07
    客运
    0.07
    WM
    0.07
    Act Density 0.010%

    No Known Activations