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

    Neuronpedia

    INDEX
    Explanations

    Anakin Skywalker, editing, dimensions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Shir
    0.91
    Kos
    0.89
    Vlad
    0.88
    Liber
    0.88
    MOR
    0.87
    Liz
    0.85
     Tatiana
    0.85
    芴
    0.85
    мо
    0.84
    Rest
    0.84
    POSITIVE LOGITS
     \|
    0.79
    WallArray
    0.79
     Иванович
    0.79
     \*
    0.78
    稆
    0.78
     Pages
    0.78
     গণ্য
    0.77
    пикир
    0.77
     برانيه
    0.76
    ൺലൈ
    0.76
    Act Density 0.001%

    No Known Activations