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

    Neuronpedia

    INDEX
    Explanations

    salts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     получ
    -0.07
    /tests
    -0.06
     coolant
    -0.06
    .Host
    -0.06
     icing
    -0.06
     sıras
    -0.06
     dům
    -0.06
    _dictionary
    -0.06
    ーチ
    -0.06
     Beitrag
    -0.06
    POSITIVE LOGITS
     ModelRenderer
    0.07
     notorious
    0.06
    кта
    0.06
    __,↵
    0.06
    ẹn
    0.06
    UIApplicationDelegate
    0.06
    .JOptionPane
    0.06
    فاق
    0.06
     urllib
    0.06
    urdu
    0.06
    Act Density 0.013%

    No Known Activations