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

    Neuronpedia

    INDEX
    Explanations

    p or n

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     گزارش
    -0.07
    таки
    -0.07
    ListOf
    -0.07
    _Api
    -0.07
     درباره
    -0.06
    Lazy
    -0.06
     Steven
    -0.06
    -side
    -0.06
    効
    -0.06
     Dispose
    -0.06
    POSITIVE LOGITS
     viewModel
    0.06
     Opinion
    0.06
     tint
    0.06
    .tx
    0.06
     parks
    0.06
     :]
    0.06
     rumor
    0.06
     револю
    0.06
    주
    0.05
     mav
    0.05
    Act Density 0.001%

    No Known Activations