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

    Neuronpedia

    INDEX
    Explanations

    Continue

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     landscapes
    -0.07
    -ad
    -0.07
     showc
    -0.06
    ĩ
    -0.06
     trip
    -0.06
     zám
    -0.06
    ارة
    -0.06
    itters
    -0.06
    Facade
    -0.06
     плеч
    -0.06
    POSITIVE LOGITS
    .Nil
    0.06
     và
    0.06
    :[↵
    0.06
    }{$
    0.06
    -Cola
    0.06
    >}↵
    0.06
    .series
    0.06
     Vậy
    0.06
    Anna
    0.06
    "]}↵
    0.06
    Act Density 0.004%

    No Known Activations