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

    Neuronpedia

    INDEX
    Explanations

    Lists

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sổ
    -0.07
    oren
    -0.07
     channels
    -0.07
    979
    -0.07
    120
    -0.06
    884
    -0.06
     Max
    -0.06
     Π
    -0.06
    ASHBOARD
    -0.06
     Blogs
    -0.06
    POSITIVE LOGITS
    "math
    0.06
     精
    0.06
     собы
    0.06
    	contentPane
    0.06
    _tD
    0.06
     knull
    0.06
    EObject
    0.06
     Saras
    0.06
     berlin
    0.06
    แนว
    0.06
    Act Density 0.062%

    No Known Activations