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
     progression
    -0.08
    gin
    -0.08
    wx
    -0.07
    前三
    -0.07
    Cli
    -0.07
     Leaves
    -0.07
    官方微博
    -0.06
     fitness
    -0.06
     seasoned
    -0.06
     cá
    -0.06
    POSITIVE LOGITS
    🔉
    0.08
    揭开
    0.08
    ,item
    0.07
    (project
    0.07
     Numerous
    0.07
    announcement
    0.07
    (lo
    0.07
    	items
    0.07
     인정
    0.07
    握住
    0.07
    Act Density 0.014%

    No Known Activations