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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     forget
    -0.08
     ath
    -0.07
    isma
    -0.06
    ");
↵
↵
    -0.06
    الأ
    -0.06
    WARD
    -0.06
     italiano
    -0.06
    UserController
    -0.06
    孙
    -0.06
    (context
    -0.06
    POSITIVE LOGITS
    永久
    0.07
    זכר
    0.07
     Chap
    0.07
    /../
    0.07
    成为中国
    0.07
    骝
    0.07
    追求
    0.07
    Slave
    0.07
     הה
    0.07
    linkedin
    0.07
    Act Density 0.010%

    No Known Activations