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

    Neuronpedia

    INDEX
    Explanations

    BU

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vectors
    -0.07
    Prov
    -0.06
    fter
    -0.06
    accumulator
    -0.06
     >",
    -0.06
     Fro
    -0.06
     lên
    -0.06
    covers
    -0.06
     Elements
    -0.06
    ίτ
    -0.06
    POSITIVE LOGITS
    _external
    0.06
    瑟
    0.06
     staples
    0.06
     Accountability
    0.06
     Charlie
    0.06
    cete
    0.06
    환경
    0.06
    antd
    0.06
     Fn
    0.06
     significance
    0.06
    Act Density 0.031%

    No Known Activations