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

    Neuronpedia

    INDEX
    Explanations

    %

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (import
    -0.07
     aliens
    -0.07
     corner
    -0.07
     knitting
    -0.06
    icity
    -0.06
    _ARGS
    -0.06
     Territory
    -0.06
    (rp
    -0.06
    idebar
    -0.06
    Author
    -0.06
    POSITIVE LOGITS
    ::/
    0.07
    .AddSingleton
    0.07
     São
    0.06
    اج
    0.06
     Созд
    0.06
    천
    0.06
     Alb
    0.06
    оці
    0.06
    %C
    0.06
     nech
    0.06
    Act Density 0.006%

    No Known Activations