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

    Neuronpedia

    INDEX
    Explanations

    browser visibility or production mode

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Hes
    0.43
    Item
    0.42
    Bracket
    0.40
    Frequently
    0.40
    Nationality
    0.39
    Location
    0.39
    Items
    0.38
    Romans
    0.38
    Length
    0.38
    Values
    0.38
    POSITIVE LOGITS
     offline
    0.45
     full
    0.43
    czych
    0.42
     Tinder
    0.40
     Offline
    0.39
     सारा
    0.38
     festival
    0.38
     draft
    0.37
     टॉ
    0.36
     hospice
    0.36
    Act Density 0.002%

    No Known Activations