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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     درآمد
    -0.07
     هستند
    -0.06
     module
    -0.06
    ασ
    -0.06
    ющими
    -0.06
    indhoven
    -0.06
    )는
    -0.06
    ение
    -0.06
     rectangular
    -0.06
    ']);
↵
    -0.06
    POSITIVE LOGITS
     Spe
    0.07
     Battles
    0.06
     Walls
    0.06
     outra
    0.06
     Leban
    0.06
    	JPanel
    0.06
    (Book
    0.06
     cling
    0.06
     scrambled
    0.06
    (fil
    0.06
    Act Density 0.005%

    No Known Activations