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

    Neuronpedia

    INDEX
    Explanations

    specific applications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     doc
    -0.07
    _UID
    -0.07
    (match
    -0.07
    喜剧
    -0.07
     мир
    -0.07
    Sign
    -0.07
    合う
    -0.07
    /out
    -0.06
     Providence
    -0.06
    Declaration
    -0.06
    POSITIVE LOGITS
    ดาร
    0.07
    _altern
    0.07
    0.07
    锑
    0.06
    gien
    0.06
    .ol
    0.06
    -the
    0.06
    arte
    0.06
     пу
    0.06
    冻
    0.06
    Act Density 0.063%

    No Known Activations