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

    Neuronpedia

    INDEX
    Explanations

    documentation links

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     machines
    -0.07
     Tanner
    -0.07
    .xhtml
    -0.07
    elidir
    -0.06
     Armstrong
    -0.06
     Norm
    -0.06
     Table
    -0.06
    １０
    -0.06
     driveway
    -0.06
    .truth
    -0.06
    POSITIVE LOGITS
     aplicación
    0.07
     život
    0.07
    ielding
    0.06
     Interface
    0.06
     »
    0.06
     Interfaces
    0.06
     Playlist
    0.06
     línea
    0.06
    (undefined
    0.06
     página
    0.06
    Act Density 0.011%

    No Known Activations