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

    Neuronpedia

    INDEX
    Explanations

    publishing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    [MAX
    -0.06
    اقع
    -0.06
     Ft
    -0.06
     Kas
    -0.06
    (direction
    -0.06
     Yu
    -0.06
    анню
    -0.06
    ктив
    -0.06
     YA
    -0.06
    FH
    -0.06
    POSITIVE LOGITS
     Cent
    0.06
    ัท
    0.06
     '<%=
    0.06
     synthesis
    0.06
    ,content
    0.06
     homeland
    0.06
    <Object
    0.06
     journal
    0.06
    dream
    0.06
     sotto
    0.06
    Act Density 0.001%

    No Known Activations