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

    Neuronpedia

    INDEX
    Explanations

    internet connection

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    119
    -0.08
    216
    -0.07
     editar
    -0.07
    215
    -0.07
    .Footer
    -0.06
    ningar
    -0.06
    ียวก
    -0.06
    213
    -0.06
     Fuse
    -0.06
    .DriverManager
    -0.06
    POSITIVE LOGITS
     pri
    0.06
     baseline
    0.06
    otts
    0.06
     десят
    0.06
     Т
    0.06
    apple
    0.06
     opted
    0.06
    -lived
    0.06
     کامپی
    0.06
     Gaut
    0.06
    Act Density 0.030%

    No Known Activations