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

    Neuronpedia

    INDEX
    Explanations

    maximizing daylight

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dimes
    0.52
     жителей
    0.45
     residents
    0.44
     maire
    0.42
     précise
    0.41
     parents
    0.40
     tickets
    0.40
     kes
    0.39
     ORIGINAL
    0.39
     entfer
    0.39
    POSITIVE LOGITS
    schema
    0.43
     ቡ
    0.38
    一个是
    0.38
    一天
    0.37
    CapsLock
    0.37
     ఒకటి
    0.37
    ール
    0.37
    सूची
    0.37
    btnUn
    0.37
     &.
    0.37
    Act Density 0.002%

    No Known Activations