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

    Neuronpedia

    INDEX
    Explanations

    -

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Gather
    -0.08
    Layers
    -0.08
    umat
    -0.08
    때
    -0.08
    Folders
    -0.08
    Chats
    -0.08
    [last
    -0.08
    bells
    -0.08
     chiropr
    -0.08
     Layers
    -0.07
    POSITIVE LOGITS
    оя
    0.08
     mo
    0.08
     मालिक
    0.08
     EPA
    0.07
    139
    0.07
     akan
    0.07
     kung
    0.07
    ific
    0.07
    141
    0.07
     EA
    0.07
    Act Density 0.002%

    No Known Activations