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

    Neuronpedia

    INDEX
    Explanations

    closets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    間
    -0.07
     اصلی
    -0.06
    ندا
    -0.06
     ensl
    -0.06
    edics
    -0.06
     Horror
    -0.06
     bourgeoisie
    -0.06
    ichtet
    -0.06
    <Post
    -0.06
     жизни
    -0.06
    POSITIVE LOGITS
    .Endpoint
    0.07
    NavLink
    0.06
     tourism
    0.06
    _PR
    0.06
     đi
    0.06
     uphold
    0.06
    assertEquals
    0.06
     Theatre
    0.06
    Ai
    0.06
     MI
    0.06
    Act Density 0.010%

    No Known Activations