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

    Neuronpedia

    INDEX
    Explanations

    shape

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    クリ
    -0.07
    CCR
    -0.07
     urinary
    -0.07
     dirent
    -0.07
    icari
    -0.06
    048
    -0.06
     introductory
    -0.06
     MySqlCommand
    -0.06
     канди
    -0.06
     Trent
    -0.06
    POSITIVE LOGITS
     shape
    0.17
     Shape
    0.15
    Shape
    0.13
     shapes
    0.13
     Shapes
    0.13
    shape
    0.11
    Shapes
    0.11
    shapes
    0.11
    .shape
    0.10
     shaping
    0.10
    Act Density 0.017%

    No Known Activations