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

    Neuronpedia

    INDEX
    Explanations

    among

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Editor
    -0.06
     Atlantis
    -0.06
    문제
    -0.06
    되어
    -0.06
    ma
    -0.06
    ่าน
    -0.06
    剂
    -0.06
    .bytes
    -0.06
     canv
    -0.06
    Hard
    -0.06
    POSITIVE LOGITS
     gấp
    0.07
     nikdo
    0.07
    _CHILD
    0.07
    DataProvider
    0.07
    Scoped
    0.06
     etwas
    0.06
    trinsic
    0.06
     forEach
    0.06
    .Selected
    0.06
     mapper
    0.06
    Act Density 0.059%

    No Known Activations