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

    Neuronpedia

    INDEX
    Explanations

    left side comparison

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     photographing
    0.47
     photography
    0.44
     Photography
    0.43
     outlining
    0.43
    拍
    0.42
     identifying
    0.42
     filming
    0.40
     visualizing
    0.39
    拍摄
    0.38
     graphing
    0.38
    POSITIVE LOGITS
     left
    1.30
    left
    1.22
    左
    1.19
    Left
    1.15
     Left
    1.12
     左
    1.04
     왼쪽
    1.04
     izquierda
    1.03
    LEFT
    1.02
     esquerda
    0.99
    Act Density 0.022%

    No Known Activations