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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     موج
    -0.07
     مستق
    -0.07
     Γεω
    -0.07
     dwind
    -0.06
     الذ
    -0.06
     IReadOnly
    -0.06
     entreg
    -0.06
     الطب
    -0.06
    fas
    -0.06
     требует
    -0.06
    POSITIVE LOGITS
    !)
    0.07
     overview
    0.07
    ог
    0.06
    200
    0.06
    .ur
    0.06
     Buildings
    0.06
     implement
    0.06
     buildings
    0.06
     Boolean
    0.06
    .predict
    0.06
    Act Density 0.001%

    No Known Activations