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

    Neuronpedia

    INDEX
    Explanations

    error

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lname
    -0.06
     Vet
    -0.06
    (Program
    -0.06
    (that
    -0.06
     nargs
    -0.06
     애
    -0.06
     onPause
    -0.06
     Federation
    -0.06
    ()",
    -0.06
     choking
    -0.06
    POSITIVE LOGITS
     Scenario
    0.07
     tut
    0.07
     выращи
    0.07
    .Sql
    0.07
     Scor
    0.06
     breakthrough
    0.06
     відб
    0.06
     проблемы
    0.06
     kısa
    0.06
    рех
    0.06
    Act Density 0.006%

    No Known Activations