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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    起点
    -0.07
    직
    -0.07
    最好是
    -0.07
    解答
    -0.07
    应该是
    -0.07
     bạc
    -0.07
    ولة
    -0.07
     Merc
    -0.07
    国家标准
    -0.07
    人民政府
    -0.07
    POSITIVE LOGITS
     hw
    0.08
     "*
    0.07
    -offsetof
    0.07
     rounds
    0.07
    cdecl
    0.07
    LOCKS
    0.07
     THIRD
    0.07
    	iter
    0.07
     flown
    0.06
     międ
    0.06
    Act Density 0.004%

    No Known Activations