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

    Neuronpedia

    INDEX
    Explanations

    right-click on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     systems
    0.41
     présents
    0.40
     loyalty
    0.40
     diurnal
    0.40
     ambitions
    0.39
    裾
    0.39
     systèmes
    0.38
     freelancer
    0.38
     үз
    0.38
     sistemas
    0.37
    POSITIVE LOGITS
    Arrange
    0.44
    扡
    0.44
    Dragging
    0.42
    Grun
    0.40
    dragging
    0.40
    Arr
    0.39
    选中
    0.39
    拖
    0.38
    Metallic
    0.38
     유리
    0.38
    Act Density 0.053%

    No Known Activations