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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Tài
    -0.07
     convention
    -0.07
    模式
    -0.07
    ancing
    -0.07
     حاج
    -0.06
    洛
    -0.06
     Ευ
    -0.06
    งก
    -0.06
     Mate
    -0.06
    顾
    -0.06
    POSITIVE LOGITS
     ApplicationController
    0.07
     equival
    0.06
     standardUserDefaults
    0.06
    inder
    0.06
     puzzled
    0.06
               ↵
    0.06
    ellungen
    0.06
    	cr
    0.06
     nghiệ
    0.06
     figured
    0.05
    Act Density 0.095%

    No Known Activations