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

    Neuronpedia

    INDEX
    Explanations

    wide

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    GraphicsUnit
    -0.69
    ########.
    -0.68
     كومونز
    -0.67
     виправивши
    -0.63
    !*\
    -0.60
    DropTable
    -0.60
     Мексичка
    -0.60
    principalColumn
    -0.58
     AssemblyCompany
    -0.57
    IndentedString
    -0.57
    POSITIVE LOGITS
     sw
    0.56
     area
    0.55
     era
    0.51
     section
    0.49
     sweep
    0.49
     gamb
    0.49
     spec
    0.48
     scope
    0.48
     are
    0.47
     age
    0.47
    Act Density 0.001%

    No Known Activations