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

    Neuronpedia

    INDEX
    Explanations

    department

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     department
    -1.65
    Department
    -1.64
     Department
    -1.59
    department
    -1.54
     DEPARTMENT
    -1.45
     Dept
    -1.33
     dept
    -1.26
     Departments
    -1.20
     departments
    -1.19
     departmental
    -1.18
    POSITIVE LOGITS
    ally
    0.58
    BeginContext
    0.52
    帖最后由
    0.52
    ALLY
    0.50
     оригіналу
    0.49
     matter
    0.48
     BoxFit
    0.47
     diri
    0.46
    اریخ
    0.45
    gridx
    0.45
    Act Density 0.127%

    No Known Activations