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

    Neuronpedia

    INDEX
    Explanations

    opinions and arguments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ीज
    -0.07
    ключ
    -0.07
    での
    -0.06
     مقایسه
    -0.06
    Mr
    -0.06
     mundane
    -0.06
    하는데
    -0.06
    _house
    -0.06
    анных
    -0.06
     BITTE
    -0.06
    POSITIVE LOGITS
     businesses
    0.06
    HEST
    0.06
     admire
    0.06
    \Collections
    0.06
     pirates
    0.06
     ABC
    0.06
    seys
    0.06
    abd
    0.06
     اخت
    0.06
    904
    0.05
    Act Density 0.039%

    No Known Activations