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

    Neuronpedia

    INDEX
    Explanations

    math problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    пор
    -0.07
    880
    -0.06
    891
    -0.06
    _sent
    -0.06
    Operators
    -0.06
    инг
    -0.06
     temperatura
    -0.06
     coordination
    -0.06
    pets
    -0.06
     europ
    -0.06
    POSITIVE LOGITS
    "));
↵
    0.06
     фіз
    0.06
    .enabled
    0.06
     navbar
    0.06
     ann
    0.06
    -Semit
    0.06
     ApplicationException
    0.06
     responseObject
    0.06
    ']))
    0.06
     перес
    0.05
    Act Density 0.021%

    No Known Activations