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

    Neuronpedia

    INDEX
    Explanations

    places and their staff

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    zn
    0.43
     Sle
    0.40
     Py
    0.39
     Yi
    0.39
    eren
    0.38
     i
    0.38
     parser
    0.38
     emulation
    0.38
    i
    0.38
     Got
    0.37
    POSITIVE LOGITS
    사장
    0.55
    党委
    0.52
    yard
    0.52
     परिसर
    0.52
    goers
    0.51
    管理者
    0.49
     ஊழிய
    0.49
    職員
    0.49
    staff
    0.48
     स्टाफ
    0.48
    Act Density 0.020%

    No Known Activations