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

    Neuronpedia

    INDEX
    Explanations

    scientific/medical studies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tours
    -0.07
     用
    -0.07
    汗
    -0.07
     sculptures
    -0.06
     fractures
    -0.06
    аном
    -0.06
    WRAPPER
    -0.06
     calculated
    -0.06
     разм
    -0.06
     hostility
    -0.06
    POSITIVE LOGITS
     》
    0.07
     Squ
    0.07
    cheduling
    0.07
    Core
    0.07
    ("../../
    0.07
     العربية
    0.07
    ptoms
    0.07
     imposs
    0.06
    _formats
    0.06
     ((*
    0.06
    Act Density 0.031%

    No Known Activations