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

    Neuronpedia

    INDEX
    Explanations

    Code/technical instructions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    מטה
    -0.07
    яти
    -0.07
     MatDialog
    -0.06
    ᱚ
    -0.06
    事项
    -0.06
    的实际
    -0.06
    ↵↵
    -0.06
    南宁
    -0.06
    🧥
    -0.06
    NegativeButton
    -0.06
    POSITIVE LOGITS
    insert
    0.07
    ourmet
    0.07
    reverse
    0.07
    Sending
    0.07
    .pack
    0.07
     glob
    0.07
    销售人员
    0.07
     IsActive
    0.06
    airs
    0.06
    这样说
    0.06
    Act Density 0.032%

    No Known Activations