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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    artz
    -0.08
     consegu
    -0.08
     świadom
    -0.08
     Quartz
    -0.07
    istema
    -0.07
    (equal
    -0.07
    ecessary
    -0.07
    צליח
    -0.07
    图为
    -0.07
    ahn
    -0.07
    POSITIVE LOGITS
    邀请
    0.07
     µ
    0.07
    VIP
    0.07
    ملاب
    0.07
     VIP
    0.07
     TBranch
    0.07
    훼
    0.07
     الديمقراطية
    0.07
     эксп
    0.07
    飲み
    0.07
    Act Density 0.130%

    No Known Activations