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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iele
    -0.07
    Things
    -0.07
     넘
    -0.07
    _membership
    -0.06
     ParameterDirection
    -0.06
    ิลล
    -0.06
     getCategory
    -0.06
    odafone
    -0.06
     prakt
    -0.06
     обл
    -0.06
    POSITIVE LOGITS
     DIC
    0.06
     signific
    0.06
    dark
    0.06
     stre
    0.06
     libero
    0.06
     encoded
    0.06
     Tar
    0.06
     exhibit
    0.06
    .!
    0.06
     banco
    0.06
    Act Density 0.009%

    No Known Activations