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

    Neuronpedia

    INDEX
    Explanations

    Code/programming language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     aeros
    -0.07
    ]):
↵
    -0.07
     Centers
    -0.07
     spel
    -0.06
     '))↵
    -0.06
    ']))↵
    -0.06
     pollen
    -0.06
     sug
    -0.06
     phot
    -0.06
    oshi
    -0.06
    POSITIVE LOGITS
     шту
    0.08
    емого
    0.07
    praak
    0.07
    cision
    0.07
     JsonRequestBehavior
    0.06
     навч
    0.06
    ческого
    0.06
     Time
    0.06
     strokes
    0.06
     إلى
    0.06
    Act Density 0.000%

    No Known Activations