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

    Neuronpedia

    INDEX
    Explanations

    walking tours

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    calendar
    0.45
    uem
    0.39
     அலுவ
    0.38
    ário
    0.38
    compute
    0.37
    ✈
    0.37
    Calendar
    0.37
    iquet
    0.36
    İK
    0.36
    computation
    0.35
    POSITIVE LOGITS
     tour
    0.50
     tours
    0.46
     highlighting
    0.46
     historias
    0.45
     сы
    0.44
     storie
    0.44
     Geschichten
    0.44
    澥
    0.44
     விளக்க
    0.43
     শহর
    0.43
    Act Density 0.017%

    No Known Activations