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

    Neuronpedia

    INDEX
    Explanations

    http

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     المنتخب
    -0.08
    ってくれ
    -0.08
     Darren
    -0.07
     Elle
    -0.07
    ",↵↵
    -0.07
     './
    -0.06
    leton
    -0.06
     ""↵
    -0.06
     Blake
    -0.06
     Wonderland
    -0.06
    POSITIVE LOGITS
    穿衣
    0.07
     seçim
    0.07
     админист
    0.07
     социально
    0.07
     objectForKey
    0.07
    adopt
    0.07
    eight
    0.07
     Classic
    0.07
    匪
    0.07
    сот
    0.07
    Act Density 0.004%

    No Known Activations