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

    Neuronpedia

    INDEX
    Explanations

    Documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     exercise
    -0.09
    exercise
    -0.08
    original
    -0.08
    Exercise
    -0.07
    TRY
    -0.07
    TIP
    -0.07
    CASE
    -0.07
    काम
    -0.07
    ercise
    -0.07
     actuality
    -0.07
    POSITIVE LOGITS
     চান
    0.13
     хотите
    0.11
     wanting
    0.11
     vuoi
    0.11
     varsa
    0.10
     deseja
    0.10
     desea
    0.10
     quieres
    0.09
     Want
    0.09
     хочет
    0.09
    Act Density 0.079%

    No Known Activations