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

    Neuronpedia

    INDEX
    Explanations

    protocol buffer files

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    547
    -0.07
    ěř
    -0.06
    りと
    -0.06
    .Title
    -0.06
     disrespect
    -0.06
    (area
    -0.06
    Av
    -0.06
     =>
↵
    -0.06
    yor
    -0.06
     cerc
    -0.06
    POSITIVE LOGITS
     möglich
    0.07
    forest
    0.07
    就
    0.07
    CASE
    0.07
    ных
    0.07
     PIXEL
    0.07
     وب
    0.07
     це
    0.06
     diğer
    0.06
     تلاش
    0.06
    Act Density 0.002%

    No Known Activations