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

    Neuronpedia

    INDEX
    Explanations

    code/data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    мм
    -0.07
     huge
    -0.07
     ноги
    -0.07
     factor
    -0.07
     #
    -0.06
     умов
    -0.06
    Physical
    -0.06
     합
    -0.06
     kvinn
    -0.06
    Proxy
    -0.06
    POSITIVE LOGITS
    352
    0.07
     gast
    0.06
    iyor
    0.06
    .Style
    0.06
    aters
    0.06
    urga
    0.06
    tribute
    0.06
    .layoutControlItem
    0.06
    	ad
    0.06
     UserProfile
    0.06
    Act Density 0.105%

    No Known Activations