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

    Neuronpedia

    INDEX
    Explanations

    include

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     telah
    -0.07
     �
    -0.07
    .sendRedirect
    -0.07
    anton
    -0.06
     linh
    -0.06
     село
    -0.06
    airobi
    -0.06
     ucz
    -0.06
    さんは
    -0.06
    、​
    -0.06
    POSITIVE LOGITS
    FIRST
    0.06
     forged
    0.06
     зміст
    0.06
     res
    0.06
    Languages
    0.06
     использу
    0.06
    ーレ
    0.06
     complete
    0.06
    iable
    0.06
     GN
    0.06
    Act Density 0.001%

    No Known Activations