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

    Neuronpedia

    INDEX
    Explanations

    Office of specific departments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ЛА
    0.41
     РО
    0.40
    ênd
    0.39
     ચૂક
    0.39
     AL
    0.39
     হিসাব
    0.38
    шла
    0.38
     Mercy
    0.38
    utis
    0.38
    ələ
    0.38
    POSITIVE LOGITS
    Office
    0.58
     office
    0.54
     Office
    0.54
     OFFICE
    0.49
     कार्यालय
    0.48
    办公室
    0.46
     அலுவலக
    0.46
    office
    0.46
     डिपार्टमेंट
    0.45
     kopi
    0.42
    Act Density 0.004%

    No Known Activations