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

    Neuronpedia

    INDEX
    Explanations

    manage

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     admit
    -0.07
     admitted
    -0.07
     lạnh
    -0.07
    Fed
    -0.07
     Users
    -0.06
    .Mutable
    -0.06
     declared
    -0.06
    .mix
    -0.06
     dam
    -0.06
     Netflix
    -0.06
    POSITIVE LOGITS
    reso
    0.07
    uvre
    0.07
     vocalist
    0.06
    看到
    0.06
    นา
    0.06
    력이
    0.06
     contentValues
    0.06
     venda
    0.06
    nek
    0.06
    .interfaces
    0.06
    Act Density 0.047%

    No Known Activations