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

    Neuronpedia

    INDEX
    Explanations

    historical periods and states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    5
    0.42
    run
    0.40
    2
    0.39
    3
    0.38
    1
    0.38
    '
    0.37
    ’
    0.37
    4
    0.36
    Bill
    0.36
    rette
    0.35
    POSITIVE LOGITS
     época
    0.46
     périodes
    0.46
    题材
    0.45
     yì
    0.44
     milestones
    0.44
     wikipagina
    0.44
    PatientR
    0.44
    പ്പോഴും
    0.43
     ateliers
    0.43
     epoca
    0.43
    Act Density 0.002%

    No Known Activations