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

    Neuronpedia

    INDEX
    Explanations

    about literature and writing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	address
    -0.06
     true
    -0.06
     其
    -0.06
     avec
    -0.06
    改变
    -0.06
     bottoms
    -0.06
     Warranty
    -0.06
     것은
    -0.06
    からは
    -0.06
    从
    -0.06
    POSITIVE LOGITS
     ASF
    0.08
     İng
    0.08
     MSC
    0.07
     enthusi
    0.07
     jsx
    0.06
    .Manifest
    0.06
     barcelona
    0.06
    IRT
    0.06
    antal
    0.06
     стор
    0.06
    Act Density 0.023%

    No Known Activations