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

    Neuronpedia

    INDEX
    Explanations

    "just" and "simply"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pol
    -0.38
     Pol
    -0.35
     Eres
    -0.33
    ↵↵
    -0.33
    migrationBuilder
    -0.33
     Salve
    -0.33
    earcher
    -0.33
    ViewStyle
    -0.32
     Cielo
    -0.32
                                   
    -0.32
    POSITIVE LOGITS
    just
    0.90
     just
    0.89
     simplemente
    0.88
    Just
    0.84
    simply
    0.83
     simply
    0.82
     JUST
    0.80
     просто
    0.73
    Simply
    0.73
     unknownFields
    0.72
    Act Density 0.109%

    No Known Activations