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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     I
    -0.07
     classifications
    -0.06
     uphol
    -0.06
     unsur
    -0.06
    _WE
    -0.06
     Haus
    -0.06
     Titan
    -0.06
     diffuse
    -0.06
     You
    -0.06
    ();↵↵
    -0.06
    POSITIVE LOGITS
    ‌خ
    0.07
    341
    0.07
     آزاد
    0.07
     tamam
    0.06
    �어
    0.06
    чила
    0.06
    ydro
    0.06
    zent
    0.06
     stealing
    0.06
     arrests
    0.06
    Act Density 0.137%

    No Known Activations