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

    Neuronpedia

    INDEX
    Explanations

    Software updates

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tells
    -0.07
     gerekti
    -0.07
    essoa
    -0.07
    overlap
    -0.07
    сос
    -0.06
     sexle
    -0.06
    ⁈
    -0.06
    	person
    -0.06
    这个游戏
    -0.06
    amoto
    -0.06
    POSITIVE LOGITS
     выполн
    0.07
    legacy
    0.07
    )">↵
    0.06
    _gift
    0.06
     spr
    0.06
    ยาว
    0.06
    IZES
    0.06
    Pane
    0.06
    ¾
    0.06
    眺
    0.06
    Act Density 0.263%

    No Known Activations