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

    Neuronpedia

    INDEX
    Explanations

    put

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /event
    -0.07
     %[
    -0.07
    无力
    -0.06
    acio
    -0.06
     satisf
    -0.06
    /ui
    -0.06
    egt
    -0.06
    suffix
    -0.06
    Loading
    -0.06
     babies
    -0.06
    POSITIVE LOGITS
     natural
    0.07
     mogła
    0.07
    不得
    0.07
    Netflix
    0.07
     contamin
    0.07
     deben
    0.06
     boring
    0.06
     corruption
    0.06
     dever
    0.06
    CategoryId
    0.06
    Act Density 0.001%

    No Known Activations