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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Blonde
    -0.07
     Exception
    -0.07
     var
    -0.06
     Var
    -0.06
     Bout
    -0.06
    Recipes
    -0.06
     JetBrains
    -0.06
     вак
    -0.06
    contest
    -0.06
     توسط
    -0.06
    POSITIVE LOGITS
    íd
    0.06
    °С
    0.06
    .Nullable
    0.06
    OD
    0.06
     Interr
    0.06
     bắc
    0.06
     İn
    0.06
    อด
    0.06
     selber
    0.06
    .FILE
    0.06
    Act Density 5.699%

    No Known Activations