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

    Neuronpedia

    INDEX
    Explanations

    code/string manipulation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cube
    -0.07
    щими
    -0.07
     üzer
    -0.07
     beverage
    -0.07
    uristic
    -0.06
    表情
    -0.06
    ETCH
    -0.06
    .sqlite
    -0.06
    (True
    -0.06
    (points
    -0.06
    POSITIVE LOGITS
     neglected
    0.06
     ranked
    0.06
     stake
    0.06
    ā
    0.06
     protect
    0.06
    sold
    0.06
     배
    0.06
     uncompressed
    0.06
    ั้
    0.06
    sell
    0.06
    Act Density 0.082%

    No Known Activations