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

    Neuronpedia

    INDEX
    Explanations

    quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
     перер
    -0.07
     trị
    -0.07
     Ipsum
    -0.06
    Floating
    -0.06
     excel
    -0.06
     sometime
    -0.06
     producing
    -0.06
     Translate
    -0.06
    監督
    -0.06
    POSITIVE LOGITS
    .school
    0.07
    ("&
    0.07
     "../
    0.07
     liken
    0.06
    едаг
    0.06
     *);↵
    0.06
     fleets
    0.06
    ")){↵
    0.06
     Belg
    0.06
     hv
    0.06
    Act Density 0.033%

    No Known Activations